path: root/refs.bib

% Journals

% First the Full Name is given, then the abbreviation used in the AMS Math
% Reviews, with an indication if it could not be found there.
% Note the 2nd overwrites the 1st, so swap them if you want the full name.

 %{AMS}
 @String{AMSTrans = "American Mathematical Society Translations" }
 @String{AMSTrans = "Amer. Math. Soc. Transl." }
 @String{BullAMS = "Bulletin of the American Mathematical Society" }
 @String{BullAMS = "Bull. Amer. Math. Soc." }
 @String{ProcAMS = "Proceedings of the American Mathematical Society" }
 @String{ProcAMS = "Proc. Amer. Math. Soc." }
 @String{TransAMS = "Transactions of the American Mathematical Society" }
 @String{TransAMS = "Trans. Amer. Math. Soc." }

 %ACM
 @String{CACM = "Communications of the {ACM}" }
 @String{CACM = "Commun. {ACM}" }
 @String{CompServ = "Comput. Surveys" }
 @String{JACM = "J. ACM" }
 @String{ACMMathSoft = "{ACM} Transactions on Mathematical Software" }
 @String{ACMMathSoft = "{ACM} Trans. Math. Software" }
 @String{SIGNUM = "{ACM} {SIGNUM} Newsletter" }
 @String{SIGNUM = "{ACM} {SIGNUM} Newslett." }

 @String{AmerSocio = "American Journal of Sociology" }
 @String{AmerStatAssoc = "Journal of the American Statistical Association" }
 @String{AmerStatAssoc = "J. Amer. Statist. Assoc." }
 @String{ApplMathComp = "Applied Mathematics and Computation" }
 @String{ApplMathComp = "Appl. Math. Comput." }
 @String{AmerMathMonthly = "American Mathematical Monthly" }
 @String{AmerMathMonthly = "Amer. Math. Monthly" }
 @String{BIT = "{BIT}" }
 @String{BritStatPsych = "British Journal of Mathematical and Statistical
          Psychology" }
 @String{BritStatPsych = "Brit. J. Math. Statist. Psych." }
 @String{CanMathBull = "Canadian Mathematical Bulletin" }
 @String{CanMathBull = "Canad. Math. Bull." }
 @String{CompApplMath = "Journal of Computational and Applied Mathematics" }
 @String{CompApplMath = "J. Comput. Appl. Math." }
 @String{CompPhys = "Journal of Computational Physics" }
 @String{CompPhys = "J. Comput. Phys." }
 @String{CompStruct = "Computers and Structures" }
 @String{CompStruct = "Comput. \& Structures" }
 @String{CompJour = "The Computer Journal" }
 @String{CompJour = "Comput. J." }
 @String{CompSysSci = "Journal of Computer and System Sciences" }
 @String{CompSysSci = "J. Comput. System Sci." }
 @String{Computing = "Computing" }
 @String{ContempMath = "Contemporary Mathematics" }
 @String{ContempMath = "Contemp. Math." }
 @String{Crelle = "Crelle's Journal" }
 @String{GiornaleMath = "Giornale di Mathematiche" }
 @String{GiornaleMath = "Giorn. Mat." } % didn't find in AMS MR., ibid.

 %IEEE
 @String{Computer = "{IEEE} Computer" }
 @String{IEEETransComp = "{IEEE} Transactions on Computers" }
 @String{IEEETransComp = "{IEEE} Trans. Comput." }
 @String{IEEETransAC = "{IEEE} Transactions on Automatic Control" }
 @String{IEEETransAC = "{IEEE} Trans. Automat. Control" }
 @String{IEEESpec = "{IEEE} Spectrum" } % didn't find in AMS MR
 @String{ProcIEEE = "Proceedings of the {IEEE}" }
 @String{ProcIEEE = "Proc. {IEEE}" } % didn't find in AMS MR
 @String{IEEETransAeroElec = "{IEEE} Transactions on Aerospace and Electronic
     Systems" }
 @String{IEEETransAeroElec = "{IEEE} Trans. Aerospace Electron. Systems" }

 @String{IMANumerAna = "{IMA} Journal of Numerical Analysis" }
 @String{IMANumerAna = "{IMA} J. Numer. Anal." }
 @String{InfProcLet = "Information Processing Letters" }
 @String{InfProcLet = "Inform. Process. Lett." }
 @String{InstMathApp = "Journal of the Institute of Mathematics and
     its Applications" }
 @String{InstMathApp = "J. Inst. Math. Appl." }
 @String{IntControl = "International Journal of Control" }
 @String{IntControl = "Internat. J. Control" }
 @String{IntNumerEng = "International Journal for Numerical Methods in
     Engineering" }
 @String{IntNumerEng = "Internat. J. Numer. Methods Engrg." }
 @String{IntSuper = "International Journal of Supercomputing Applications" }
 @String{IntSuper = "Internat. J. Supercomputing Applic." } % didn't find
%% in AMS MR
 @String{Kibernetika = "Kibernetika" }
 @String{JResNatBurStand = "Journal of Research of the National Bureau
     of Standards" }
 @String{JResNatBurStand = "J. Res. Nat. Bur. Standards" }
 @String{LinAlgApp = "Linear Algebra and its Applications" }
 @String{LinAlgApp = "Linear Algebra Appl." }
 @String{MathAnaAppl = "Journal of Mathematical Analysis and Applications" }
 @String{MathAnaAppl = "J. Math. Anal. Appl." }
 @String{MathAnnalen = "Mathematische Annalen" }
 @String{MathAnnalen = "Math. Ann." }
 @String{MathPhys = "Journal of Mathematical Physics" }
 @String{MathPhys = "J. Math. Phys." }
 @String{MathComp = "Mathematics of Computation" }
 @String{MathComp = "Math. Comp." }
 @String{MathScand = "Mathematica Scandinavica" }
 @String{MathScand = "Math. Scand." }
 @String{TablesAidsComp = "Mathematical Tables and Other Aids to Computation" }
 @String{TablesAidsComp = "Math. Tables Aids Comput." }
 @String{NumerMath = "Numerische Mathematik" }
 @String{NumerMath = "Numer. Math." }
 @String{PacificMath = "Pacific Journal of Mathematics" }
 @String{PacificMath = "Pacific J. Math." }
 @String{ParDistComp = "Journal of Parallel and Distributed Computing" }
 @String{ParDistComp = "J. Parallel and Distrib. Comput." } % didn't find
%% in AMS MR
 @String{ParComputing = "Parallel Computing" }
 @String{ParComputing = "Parallel Comput." }
 @String{PhilMag = "Philosophical Magazine" }
 @String{PhilMag = "Philos. Mag." }
 @String{ProcNAS = "Proceedings of the National Academy of Sciences
                    of the USA" }
 @String{ProcNAS = "Proc. Nat. Acad. Sci. U. S. A." }
 @String{Psychometrika = "Psychometrika" }
 @String{QuartMath = "Quarterly Journal of Mathematics, Oxford, Series (2)" }
 @String{QuartMath = "Quart. J. Math. Oxford Ser. (2)" }
 @String{QuartApplMath = "Quarterly of Applied Mathematics" }
 @String{QuartApplMath = "Quart. Appl. Math." }
 @String{RevueInstStat = "Review of the International Statisical Institute" }
 @String{RevueInstStat = "Rev. Inst. Internat. Statist." }

 %SIAM
 @String{JSIAM = "Journal of the Society for Industrial and Applied
     Mathematics" }
 @String{JSIAM = "J. Soc. Indust. Appl. Math." }
 @String{JSIAMB = "Journal of the Society for Industrial and Applied
     Mathematics, Series B, Numerical Analysis" }
 @String{JSIAMB = "J. Soc. Indust. Appl. Math. Ser. B Numer. Anal." }
 @String{SIAMAlgMeth = "{SIAM} Journal on Algebraic and Discrete Methods" }
 @String{SIAMAlgMeth = "{SIAM} J. Algebraic Discrete Methods" }
 @String{SIAMAppMath = "{SIAM} Journal on Applied Mathematics" }
 @String{SIAMAppMath = "{SIAM} J. Appl. Math." }
 @String{SIAMComp = "{SIAM} Journal on Computing" }
 @String{SIAMComp = "{SIAM} J. Comput." }
 @String{SIAMMatrix = "{SIAM} Journal on Matrix Analysis and Applications" }
 @String{SIAMMatrix = "{SIAM} J. Matrix Anal. Appl." }
 @String{SIAMNumAnal = "{SIAM} Journal on Numerical Analysis" }
 @String{SIAMNumAnal = "{SIAM} J. Numer. Anal." }
 @String{SIAMReview = "{SIAM} Review" }
 @String{SIAMReview = "{SIAM} Rev." }
 @String{SIAMSciStat = "{SIAM} Journal on Scientific and Statistical
     Computing" }
 @String{SIAMSciStat = "{SIAM} J. Sci. Statist. Comput." }

 @String{SoftPracExp = "Software Practice and Experience" }
 @String{SoftPracExp = "Software Prac. Experience" } % didn't find in AMS MR
 @String{StatScience = "Statistical Science" }
 @String{StatScience = "Statist. Sci." }
 @String{Techno = "Technometrics" }
 @String{USSRCompMathPhys = "{USSR} Computational Mathematics and Mathematical
     Physics" }
 @String{USSRCompMathPhys = "{U. S. S. R.} Comput. Math. and Math. Phys." }
 @String{VLSICompSys = "Journal of {VLSI} and Computer Systems" }
 @String{VLSICompSys = "J. {VLSI} Comput. Syst." }
 @String{ZAngewMathMech = "Zeitschrift fur Angewandte Mathematik und
     Mechanik" }
 @String{ZAngewMathMech = "Z. Angew. Math. Mech." }
 @String{ZAngewMathPhys = "Zeitschrift fur Angewandte Mathematik und Physik" }
 @String{ZAngewMathPhys = "Z. Angew. Math. Phys." }

% Publishers % ================================================= |

 @String{Academic = "Academic Press" }
 @String{ACMPress = "{ACM} Press" }
 @String{AdamHilger = "Adam Hilger" }
 @String{AddisonWesley = "Addison-Wesley" }
 @String{AllynBacon = "Allyn and Bacon" }
 @String{AMS = "American Mathematical Society" }
 @String{Birkhauser = "Birkha{\"u}ser" }
 @String{CambridgePress = "Cambridge University Press" }
 @String{Chelsea = "Chelsea" }
 @String{ClaredonPress = "Claredon Press" }
 @String{DoverPub = "Dover Publications" }
 @String{Eyolles = "Eyolles" }
 @String{HoltRinehartWinston = "Holt, Rinehart and Winston" }
 @String{Interscience = "Interscience" }
 @String{JohnsHopkinsPress = "The Johns Hopkins University Press" }
 @String{JohnWileySons = "John Wiley and Sons" }
 @String{Macmillan = "Macmillan" }
 @String{MathWorks = "The Math Works Inc." }
 @String{McGrawHill = "McGraw-Hill" }
 @String{NatBurStd = "National Bureau of Standards" }
 @String{NorthHolland = "North-Holland" }
 @String{OxfordPress = "Oxford University Press" }  %address Oxford or London?
 @String{PergamonPress = "Pergamon Press" }
 @String{PlenumPress = "Plenum Press" }
 @String{PrenticeHall = "Prentice-Hall" }
 @String{SIAMPub = "{SIAM} Publications" }
 @String{Springer = "Springer-Verlag" }
 @String{TexasPress = "University of Texas Press" }
 @String{VanNostrand = "Van Nostrand" }
 @String{WHFreeman = "W. H. Freeman and Co." }

%Entries

@inproceedings{DBLP:conf/nips/BrownMRSKDNSSAA20,
  author       = {Tom B. Brown and
                  Benjamin Mann and others},
  title        = {Language Models are Few-Shot Learners},
  booktitle    = {NeurIPS},
  year         = {2020}
}

@article{DBLP:journals/corr/abs-2107-03374,
  author       = {Mark Chen and
                  Jerry Tworek and others},
  title        = {Evaluating Large Language Models Trained on Code},
  journal      = {arXiv:2107.03374},
  year         = {2021}
}

@article{DBLP:journals/corr/abs-2303-08774,
  author       = {OpenAI},
  title        = {{GPT-4} Technical Report},
  journal      = {arXiv:2303.08774},
  year         = {2023}
}

@article{LLaMA,
  author       = {Hugo Touvron and
                  Thibaut Lavril and others},
  title        = {LLaMA: Open and Efficient Foundation Language Models},
  journal      = {arXiv:2302.13971},
  year         = {2023}
}

@article{DBLP:journals/corr/abs-2307-09288,
  author       = {Hugo Touvron and
                  Louis Martin and others},
  title        = {Llama 2: Open Foundation and Fine-Tuned Chat Models},
  journal      = {arXiv:2307.09288},
  year         = {2023}
}

@article{DBLP:journals/corr/abs-2308-12950,
  author       = {Baptiste Rozi{\`{e}}re and
                  Jonas Gehring and others},
  title        = {Code Llama: Open Foundation Models for Code},
  journal      = {arXiv:2308.12950},
  year         = {2023}
}

@inproceedings{DBLP:conf/icml/RameshPGGVRCS21,
  author       = {Aditya Ramesh and
                  Mikhail Pavlov and
                  Gabriel Goh and others},
  title        = {Zero-Shot Text-to-Image Generation},
  booktitle    = {{ICML}},
  year         = {2021}
}

@article{DBLP:journals/corr/abs-2204-06125,
  author       = {Aditya Ramesh and
                  Prafulla Dhariwal and
                  Alex Nichol and others},
  title        = {Hierarchical Text-Conditional Image Generation with {CLIP} Latents},
  journal      = {arXiv:2204.06125},
  year         = {2022}
}

@article{betker2023improving,
  title={Improving image generation with better captions},
  author={Betker, James and Goh, Gabriel and Jing, Li and others},
  journal={Computer Science},
  volume={2},
  number={3},
  pages={8},
  year={2023}
}

@inproceedings{DBLP:conf/cvpr/RombachBLEO22,
  author       = {Robin Rombach and
                  Andreas Blattmann and
                  Dominik Lorenz and others},
  title        = {High-Resolution Image Synthesis with Latent Diffusion Models},
  booktitle    = {{IEEE/CVF}},
  year         = {2022}
}

@misc{openai/sora,
    author = {OpenAI},
    year = {2024},
    title = {Video generation models as world simulators},
    howpublished = {\url{https://openai.com/research/video-generation-models-as-world-simulators}},
}

@article{GAN,
  title={Generative adversarial networks},
  author={Goodfellow, Ian and Pouget-Abadie, Jean and Mirza, Mehdi and others},
  journal={CACM},
  volume={63},
  number={11},
  pages={139--144},
  year={2020}
}

@article{DBLP:journals/neco/HochreiterS97,
  author       = {Sepp Hochreiter and
                  J{\"{u}}rgen Schmidhuber},
  title        = {Long Short-Term Memory},
  journal      = {Neural Comput.},
  volume       = {9},
  number       = {8},
  pages        = {1735--1780},
  year         = {1997}
}

@inproceedings{DBLP:conf/nips/VaswaniSPUJGKP17,
  author       = {Ashish Vaswani and
                  Noam Shazeer and
                  Niki Parmar and others},
  title        = {Attention is All you Need},
  booktitle    = {NeurIPS},
  year         = {2017}
}

@inproceedings{DBLP:conf/iclr/GuoRLFT0ZDSFTDC21,
  author       = {Daya Guo and
                  Shuo Ren and others},
  title        = {GraphCodeBERT: Pre-training Code Representations with Data Flow},
  booktitle    = {ICLR},
  year         = {2021}
}

@article{DBLP:journals/jmlr/RaffelSRLNMZLL20,
  author       = {Colin Raffel and
                  Noam Shazeer and
                  Adam Roberts and others},
  title        = {Exploring the Limits of Transfer Learning with a Unified Text-to-Text
                  Transformer},
  journal      = {JMLR},
  volume       = {21},
  pages        = {140:1--140:67},
  year         = {2020}
}

@article{Switch_transformers,
  title={Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity},
  author={Fedus, William and Zoph, Barret and Shazeer, Noam},
  journal={JMLR},
  volume={23},
  number={120},
  pages={1--39},
  year={2022}
}

@article{scalingLaw,
  author       = {Jared Kaplan and
                  Sam McCandlish and
                  Tom Henighan and others},
  title        = {Scaling Laws for Neural Language Models},
  year         = {2020},
  eprinttype    = {arXiv}
}

@article{DBLP:journals/ftir/RobertsonZ09,
  author       = {Stephen E. Robertson and
                  Hugo Zaragoza},
  title        = {The Probabilistic Relevance Framework: {BM25} and Beyond},
  journal      = {FTIR},
  volume       = {3},
  number       = {4},
  pages        = {333--389},
  year         = {2009}
}

@inproceedings{DBLP:conf/emnlp/KarpukhinOMLWEC20,
  author       = {Vladimir Karpukhin and
                  Barlas Oguz and
                  Sewon Min and others},
  title        = {Dense Passage Retrieval for Open-Domain Question Answering},
  booktitle    = {{EMNLP}},
  year         = {2020}
}

@article{DBLP:journals/tbd/JohnsonDJ21,
  author       = {Jeff Johnson and
                  Matthijs Douze and
                  Herv{\'{e}} J{\'{e}}gou},
  title        = {Billion-Scale Similarity Search with GPUs},
  journal      = {{IEEE} Trans. Big Data},
  volume       = {7},
  number       = {3},
  pages        = {535--547},
  year         = {2021}
}

@inproceedings{DBLP:conf/nips/ChenZWLLLYW21,
  author       = {Qi Chen and
                  Bing Zhao and
                  Haidong Wang and others},
  title        = {{SPANN:} Highly-efficient Billion-scale Approximate Nearest Neighborhood
                  Search},
  booktitle    = {NeurIPS},
  year         = {2021}
}

@article{DBLP:journals/csur/DattaJLW08,
  author       = {Ritendra Datta and
                  Dhiraj Joshi and
                  Jia Li and others},
  title        = {Image retrieval: Ideas, influences, and trends of the new age},
  journal      = {CSUR},
  volume       = {40},
  number       = {2},
  pages        = {5:1--5:60},
  year         = {2008}
}

@inproceedings{radford2021learning,
  title={Learning transferable visual models from natural language supervision},
  author={Radford, Alec and Kim, Jong Wook and Hallacy, Chris and others},
  booktitle={ICML},
  year={2021}
}

@inproceedings{DBLP:conf/emnlp/FengGTDFGS0LJZ20,
  author       = {Zhangyin Feng and
                  Daya Guo and others},
  title        = {CodeBERT: {A} Pre-Trained Model for Programming and Natural Languages},
  booktitle    = {EMNLP Findings},
  year         = {2020}
}

@inproceedings{DBLP:conf/icassp/WuCZHBD23,
  author       = {Yusong Wu and
                  Ke Chen and
                  Tianyu Zhang and others},
  title        = {Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion
                  and Keyword-to-Caption Augmentation},
  booktitle    = {ICASSP},
  year         = {2023}
}

@inproceedings{Adaptive-Retrieval-whennottrust,
  author       = {Alex Mallen and
                  Akari Asai and
                  Victor Zhong and others},
  title        = {When Not to Trust Language Models: Investigating Effectiveness of
                  Parametric and Non-Parametric Memories},
  booktitle    = {ACL},
  year         = {2023},

}

@inproceedings{DBLP:conf/uss/CarliniTWJHLRBS21,
  author       = {Nicholas Carlini and
                  Florian Tram{\`{e}}r and others},
  title        = {Extracting Training Data from Large Language Models},
  booktitle    = {{USENIX}},
  year         = {2021}
}

@article{C-RAG,
  author       = {Mintong Kang and
                  Nezihe Merve G{\"{u}}rel and others},
  title        = {{C-RAG:} Certified Generation Risks for Retrieval-Augmented Language
                  Models},
  journal      = {arXiv:2402.03181},
  year         = {2024}
}

@article{Atlas,
  author={Izacard, Gautier and Lewis, Patrick and Lomeli, Maria and others}, 
  title={Atlas: Few-shot learning with retrieval augmented language models},
  journal={arXiv:2208.03299},
  year={2022}
}

@inproceedings{MemTransformer2022,
  author       = {Yuhuai Wu and
                  Markus Norman Rabe and
                  DeLesley Hutchins and
                  Christian Szegedy},
  title        = {Memorizing Transformers},
  booktitle    = {ICLR},
  year         = {2022},

}

@article{REST,
  author       = {Zhenyu He and
                  Zexuan Zhong and
                  Tianle Cai and others},
  title        = {{REST:} Retrieval-Based Speculative Decoding},
  journal      = {arxiv:2311.08252},
  year         = {2023}
}

@article{REALM,
  author       = {Kelvin Guu and
                  Kenton Lee and
                  Zora Tung and others},
  title        = {{REALM:} Retrieval-Augmented Language Model Pre-Training},
  journal      = {ICML},
  year         = {2020}
}

@inproceedings{2020RAG,
  author       = {Patrick S. H. Lewis and
                  Ethan Perez and
                  Aleksandra Piktus and others},
  title        = {Retrieval-Augmented Generation for Knowledge-Intensive {NLP} Tasks},
  booktitle    = {NeurIPS},
  year         = {2020},
}

@inproceedings{FID,
  author       = {Gautier Izacard and
                  Edouard Grave},
  title        = {Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering},
  booktitle    = {{EACL}},
  year         = {2021}
}

@inproceedings{RETRO,
  author       = {Sebastian Borgeaud and
                  Arthur Mensch and others},
  title        = {Improving Language Models by Retrieving from Trillions of Tokens},
  booktitle    = {{ICML}},
  year         = {2022}
}

@inproceedings{KNN-LM,
  author       = {Urvashi Khandelwal and
                  Omer Levy and
                  Dan Jurafsky and others},
  title        = {Generalization through Memorization: Nearest Neighbor Language Models},
  booktitle    = {ICLR},
  year         = {2020},
}

@inproceedings{Efficient-KNNLM,
  author       = {Junxian He and
                  Graham Neubig and
                  Taylor Berg{-}Kirkpatrick},
  title        = {Efficient Nearest Neighbor Language Models},
  booktitle    = {EMNLP},
  year         = {2021},

}

@online{GPTCache,
  author =    {zilliztech},
  title =  {GPTCache},
  year = 2023,
  url =    {https://github.com/zilliztech/GPTCache},
  }

  @inproceedings{DBLP:conf/emnlp/ParvezACRC21,
  author       = {Md. Rizwan Parvez and
                  Wasi Uddin Ahmad and others},
  title        = {Retrieval Augmented Code Generation and Summarization},
  booktitle    = {EMNLP Findings},
  year         = {2021}
}

@inproceedings{DBLP:conf/naacl/AhmadCRC21,
  author       = {Wasi Uddin Ahmad and
                  Saikat Chakraborty and
                  Baishakhi Ray and others},
  title        = {Unified Pre-training for Program Understanding and Generation},
  booktitle    = {NAACL-HLT},
  year         = {2021}
}

@inproceedings{DBLP:conf/iclr/Zhou0XJN23,
  author       = {Shuyan Zhou and
                  Uri Alon and
                  Frank F. Xu and others},
  title        = {DocPrompting: Generating Code by Retrieving the Docs},
  booktitle    = {ICLR},
  year         = {2023}
}

@article{DBLP:journals/corr/abs-2012-07331,
  title={Audio captioning using pre-trained large-scale language model guided by audio-based similar caption retrieval},
  author={Koizumi, Yuma and Ohishi, Yasunori and others},
  journal={arXiv:2012.07331},
  year={2020}
}

@inproceedings{DBLP:conf/icml/HuangHY0LLYLYZ23,
  author       = {Rongjie Huang and
                  Jiawei Huang and
                  Dongchao Yang and others},
  title        = {Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion
                  Models},
  booktitle    = {ICML},
  year         = {2023}
}

@inproceedings{tseng2020retrievegan,
  title={Retrievegan: Image synthesis via differentiable patch retrieval},
  author={Tseng, Hung-Yu and Lee, Hsin-Ying and others},
  booktitle={ECCV},
  year={2020}
}

@inproceedings{sarto2022retrieval,
  title={Retrieval-augmented transformer for image captioning},
  author={Sarto, Sara and Cornia, Marcella and Baraldi, Lorenzo and Cucchiara, Rita},
  booktitle={CBMI},
  year={2022}
}

@inproceedings{ramos2023smallcap,
  title={SmallCap: lightweight image captioning prompted with retrieval augmentation},
  author={Ramos, Rita and Martins, Bruno and others},
  booktitle={CVPR},
  year={2023}
}

@article{DBLP:journals/tomccap/ChenPLYCM23,
  author       = {Jingwen Chen and
                  Yingwei Pan and
                  Yehao Li and others},
  title        = {Retrieval Augmented Convolutional Encoder-decoder Networks for Video
                  Captioning},
  journal      = {TOMCCAP},
  volume       = {19},
  number       = {1s},
  pages        = {48:1--48:24},
  year         = {2023}
}

@article{DBLP:journals/corr/abs-2401-00789,
  author       = {Jilan Xu and
                  Yifei Huang and
                  Junlin Hou and others},
  title        = {Retrieval-Augmented Egocentric Video Captioning},
  journal      = {arXiv:2401.00789},
  year         = {2024}
}

@article{DBLP:journals/corr/abs-2402-02972,
  title={Retrieval-augmented score distillation for text-to-3d generation},
  author={Seo, Junyoung and Hong, Susung and others},
  journal={arXiv:2402.02972},
  year={2024}
}

@inproceedings{DBLP:conf/iccv/ZhangGPCHLYL23,
  author       = {Mingyuan Zhang and
                  Xinying Guo and
                  Liang Pan and others},
  title        = {ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model},
  booktitle    = {ICCV},
  year         = {2023}
}

@inproceedings{DBLP:conf/coling/HuWSQ22,
  author       = {Xixin Hu and
                  Xuan Wu and
                  Yiheng Shu and
                  Yuzhong Qu},
  title        = {Logical Form Generation via Multi-task Learning for Complex Question Answering over Knowledge Bases},
  booktitle    = {COLING},
  year         = {2022}
}

@inproceedings{DBLP:conf/emnlp/HuangKZ21,
  author       = {Xin Huang and
                  Jung{-}Jae Kim and
                  Bowei Zou},
  title        = {Unseen Entity Handling in Complex Question Answering over Knowledge Base via Language Generation},
  booktitle    = {EMNLP Findings},
  year         = {2021}
}

@inproceedings{DBLP:conf/emnlp/DasZTGPLTPM21,
  author       = {Rajarshi Das and
                  Manzil Zaheer and
                  Dung Thai and others},
  title        = {Case-based Reasoning for Natural Language Queries over Knowledge Bases},
  booktitle    = {EMNLP},
  year         = {2021}
}

@inproceedings{wang2022retrieval,
  title={Retrieval-based Controllable Molecule Generation},
  author={Wang, Zichao and Nie, Weili and Qiao, Zhuoran and others},
  booktitle={ICLR},
  year={2022}
}

@article{jin2023genegpt,
  title={Genegpt: Augmenting large language models with domain tools for improved access to biomedical information},
  author={Jin, Qiao and Yang, Yifan and Chen, Qingyu and Lu, Zhiyong},
  journal={Bioinformatics},
  volume={40},
  number={2},
  pages={btae075},
  year={2024}
}

@article{DBLP:journals/corr/abs-2202-01110,
  author       = {Huayang Li and
                  Yixuan Su and
                  Deng Cai and others},
  title        = {A Survey on Retrieval-Augmented Text Generation},
  journal      = {arxiv:2202.01110},
  year         = {2022}
}

@article{retrieval-lm-tutorial,
  author    = { Asai, Akari and Min, Sewon and Zhong, Zexuan and Chen, Danqi },
  title     = { ACL 2023 Tutorial: Retrieval-based Language Models and Applications },
  journal   = { ACL 2023 },
  year      = { 2023 },
}

@article{DBLP:journals/corr/abs-2312-10997,
  author       = {Yunfan Gao and
                  Yun Xiong and others},
  title        = {Retrieval-Augmented Generation for Large Language Models: {A} Survey},
  journal      = {arxiv:2312.10997},
  year         = {2023}
}

@inproceedings{DBLP:conf/emnlp/ZhaoCWJLQDGLLJ23,
  author       = {Ruochen Zhao and
                  Hailin Chen and others},
  title        = {Retrieving Multimodal Information for Augmented Generation: {A} Survey},
  booktitle    = {{EMNLP}},
  year         = {2023}
}

@article{ding2024survey,
  title={A Survey on RAG Meets LLMs: Towards Retrieval-Augmented Large Language Models},
  author={Ding, Yujuan and Fan, Wenqi and others},
  journal={arXiv:2405.06211},
  year={2024}
}

@inproceedings{DBLP:conf/cvpr/ChenGY0E22,
  author       = {Jun Chen and
                  Han Guo and
                  Kai Yi and others},
  title        = {VisualGPT: Data-efficient Adaptation of Pretrained Language Models
                  for Image Captioning},
  booktitle    = {{CVPR}},
  year         = {2022}
}

@article{EfficientTransformers,
  author       = {Yi Tay and
                  Mostafa Dehghani and
                  Dara Bahri and
                  Donald Metzler},
  title        = {Efficient Transformers: {A} Survey},
  journal      = {CSUR},
  volume       = {55},
  number       = {6},
  pages        = {109:1--109:28},
  year         = {2023}
}

@article{lstm_survey,
  author       = {Greg Van Houdt and others},
  title        = {A review on the long short-term memory model},
  journal      = {Artif. Intell. Rev.},
  volume       = {53},
  number       = {8},
  pages        = {5929--5955},
  year         = {2020}
}

@article{yang2023diffsurvey,
  title={Diffusion models: A comprehensive survey of methods and applications},
  author={Yang, Ling and Zhang, Zhilong and others},
  journal={CSUR},
  volume={56},
  number={4},
  pages={1--39},
  year={2023}
}

@article{GAN_Survey,
  author       = {Jie Gui and
                  Zhenan Sun and
                  Yonggang Wen and others},
  title        = {A Review on Generative Adversarial Networks: Algorithms, Theory, and
                  Applications},
  journal      = {TKDE},
  volume       = {35},
  number       = {4},
  pages        = {3313--3332},
  year         = {2023}
}

@inproceedings{DBLP:conf/sigir/RobertsonW97,
  author       = {Stephen E. Robertson and
                  Steve Walker},
  title        = {On Relevance Weights with Little Relevance Information},
  booktitle    = {{SIGIR}},
  year         = {1997}
}

@inproceedings{DBLP:conf/sigir/LaffertyZ01,
  author       = {John D. Lafferty and
                  ChengXiang Zhai},
  title        = {Document Language Models, Query Models, and Risk Minimization for
                  Information Retrieval},
  booktitle    = {SIGIR},
  year         = {2001}
}

@inproceedings{DBLP:conf/icassp/HersheyCEGJMPPS17,
  author       = {Shawn Hershey and
                  Sourish Chaudhuri and others},
  title        = {{CNN} architectures for large-scale audio classification},
  booktitle    = {ICASSP},
  year         = {2017}
}

@inproceedings{DBLP:conf/cvpr/DongLXJH0W19,
  author       = {Jianfeng Dong and
                  Xirong Li and
                  Chaoxi Xu and others},
  title        = {Dual Encoding for Zero-Example Video Retrieval},
  booktitle    = {CVPR},
  year         = {2019},
}

@inproceedings{DBLP:conf/iclr/XiongXLTLBAO21,
  author       = {Lee Xiong and
                  Chenyan Xiong and
                  Ye Li and others},
  title        = {Approximate Nearest Neighbor Negative Contrastive Learning for Dense
                  Text Retrieval},
  booktitle    = {{ICLR}},
  year         = {2021}
}

@article{bentley1975multidimensional,
  title={Multidimensional binary search trees used for associative searching},
  author={Bentley, Jon Louis},
  journal={CACM},
  volume={18},
  number={9},
  pages={509--517},
  year={1975}
}

@inproceedings{li2023learning,
  title={Learning balanced tree indexes for large-scale vector retrieval},
  author={Li, Wuchao and Feng, Chao and Lian, Defu and others},
  booktitle={SIGKDDg},
  year={2023}
}

@inproceedings{datar2004locality,
  title={Locality-sensitive hashing scheme based on p-stable distributions},
  author={Datar, Mayur and Immorlica, Nicole and Indyk, Piotr and others},
  booktitle={SCG},
  year={2004}
}

@article{malkov2018efficient,
  title={Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs},
  author={Malkov, Yu A and Yashunin, Dmitry A},
  journal={TPAMI},
  volume={42},
  number={4},
  pages={824--836},
  year={2018}
}

@article{jayaram2019diskann,
  title={Diskann: Fast accurate billion-point nearest neighbor search on a single node},
  author={Jayaram Subramanya, Suhas and Devvrit, Fnu and others},
  journal={NeurIPS},
  year={2019}
}

@inproceedings{DBLP:conf/nips/WangHWMWCXCZL0022,
  author       = {Yujing Wang and
                  Yingyan Hou and
                  Haonan Wang and others},
  title        = {A Neural Corpus Indexer for Document Retrieval},
  booktitle    = {NeurIPS},
  year         = {2022}
}

@inproceedings{DBLP:conf/nips/ZhangWCCZMHDMWP23,
  author       = {Hailin Zhang and
                  Yujing Wang and
                  Qi Chen and others},
  title        = {Model-enhanced Vector Index},
  booktitle    = {NeurIPS},
  year         = {2023}
}

@inproceedings{DBLP:conf/emnlp/HayatiOAYTN18,
  author       = {Shirley Anugrah Hayati and
                  Rapha{\"{e}}l Olivier and
                  Pravalika Avvaru and others},
  title        = {Retrieval-Based Neural Code Generation},
  booktitle    = {EMNLP},
  year         = {2018}
}

@inproceedings{DBLP:conf/icse/ZhangW00020,
  author       = {Jian Zhang and
                  Xu Wang and
                  Hongyu Zhang and others},
  title        = {Retrieval-based neural source code summarization},
  booktitle    = {ICSE},
  year         = {2020}
}

@inproceedings{DBLP:conf/iclr/PoesiaP00SMG22,
  author       = {Gabriel Poesia and
                  Alex Polozov and
                  Vu Le and others},
  title        = {Synchromesh: Reliable Code Generation from Pre-trained Language Models},
  booktitle    = {ICLR},
  year         = {2022}
}

@inproceedings{DBLP:conf/acl/YeYHZX22,
  author       = {Xi Ye and
                  Semih Yavuz and others},
  title        = {{RNG-KBQA:} Generation Augmented Iterative Ranking for Knowledge Base Question Answering},
  booktitle    = {ACL},
  year         = {2022}
}

@article{DBLP:journals/corr/abs-2210-12925,
  author       = {Yiheng Shu and
                  Zhiwei Yu  others},
  title        = {{TIARA:} Multi-grained Retrieval for Robust Question Answering over Large Knowledge Bases},
  journal      = {arXiv:2210.12925},
  year         = {2022}
}

@article{lin2020bridging,
  title={Bridging textual and tabular data for cross-domain text-to-sql semantic parsing},
  author={Lin, Xi Victoria and Socher, Richard and others},
  journal={arXiv:2012.12627},
  year={2020}
}

@article{Self-RAG,
  author       = {Akari Asai and
                  Zeqiu Wu and
                  Yizhong Wang and others},
  title        = {Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection},
  journal      = {arxiv:2310.11511},
  year         = {2023}
}

@article{REPLUG,
  title={Replug: Retrieval-augmented black-box language models},
  author={Shi, Weijia and Min, Sewon and Yasunaga, Michihiro and others},
  journal={arXiv:2301.12652},
  year={2023}
}

@article{RALM,
  title={In-context retrieval-augmented language models},
  author={Ram, Ori and Levine, Yoav and Dalmedigos, Itay and others},
  journal={arXiv:2302.00083},
  year={2023}
}

@inproceedings{DBLP:conf/emnlp/ZanCLGWL22,
  author       = {Daoguang Zan and
                  Bei Chen and
                  Zeqi Lin and others},
  title        = {When Language Model Meets Private Library},
  booktitle    = {EMNLP Findings},
  year         = {2022}
}

@inproceedings{DBLP:conf/icse/NashidSM23,
  author       = {Noor Nashid and
                  Mifta Sintaha and
                  Ali Mesbah},
  title        = {Retrieval-Based Prompt Selection for Code-Related Few-Shot Learning},
  booktitle    = {ICSE},
  year         = {2023}
}

@inproceedings{DBLP:conf/sigsoft/JinSTSLSS23,
  author       = {Matthew Jin and
                  Syed Shahriar and
                  Michele Tufano and others},
  title        = {InferFix: End-to-End Program Repair with LLMs},
  booktitle    = {ESEC/FSE},
  year         = {2023}
}

@inproceedings{DBLP:conf/acl/LuDHGHS22,
  author       = {Shuai Lu and
                  Nan Duan and
                  Hojae Han and others},
  title        = {ReACC: {A} Retrieval-Augmented Code Completion Framework},
  booktitle    = {ACL},
  year         = {2022}
}

@inproceedings{DBLP:conf/acl/Liu22,
    title = "Uni-Parser: Unified Semantic Parser for Question Answering on Knowledge Base and Database",
    author = "Liu, Ye  and
      Yavuz, Semih  and
      Meng, Rui  and
      Radev, Dragomir  and
      Xiong, Caiming  and
      Zhou, Yingbo",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.emnlp-main.605/",
    doi = "10.18653/v1/2022.emnlp-main.605",
    pages = "8858--8869",
    abstract = "Parsing natural language questions into executable logical forms is a useful and interpretable way to perform question answering on structured data such as knowledge bases (KB) or databases (DB). However, existing approaches on semantic parsing cannot adapt to both modalities, as they suffer from the exponential growth of the logical form candidates and can hardly generalize to unseen data.In this work, we propose Uni-Parser, a unified semantic parser for question answering (QA) on both KB and DB. We define the primitive (relation and entity in KB, and table name, column name and cell value in DB) as the essential element in our framework. The number of primitives grows only at a linear rate to the number of retrieved relations in KB and DB, preventing us from exponential logic form candidates. We leverage the generator to predict final logical forms by altering and composing top-ranked primitives with different operations (e.g. select, where, count). With sufficiently pruned search space by a contrastive primitive ranker, the generator is empowered to capture the composition of primitives enhancing its generalization ability. We achieve competitive results on multiple KB and DB QA benchmarks with more efficiency, especially in the compositional and zero-shot settings."
}

@inproceedings{DBLP:conf/eacl/YangDCC23,
  author       = {Zonglin Yang and
                  Xinya Du and
                  Erik Cambria and others},
  title        = {End-to-end Case-Based Reasoning for Commonsense Knowledge Base Completion},
  booktitle    = {EACL},
  year         = {2023}
}

@inproceedings{shi2023retrieval,
  author={Shi, Wenqi and Zhuang, Yuchen and Zhu, Yuanda and others},
  title={Retrieval-augmented large language models for adolescent idiopathic scoliosis patients in shared decision-making},
  booktitle={ACM-BCB},
  year={2023}
}

@inproceedings{casanova2021instance,
  title={Instance-conditioned gan},
  author={Casanova, Arantxa and Careil, Marlene and Verbeek, Jakob and others},
  booktitle={NeurIPS},
  year={2021}
}

@article{Bertsch2023UnlimiformerLT,
  author       = {Amanda Bertsch and
                  Uri Alon and
                  Graham Neubig and
                  Matthew R. Gormley},
  title        = {Unlimiformer: Long-Range Transformers with Unlimited Length Input},
  booktitle     = {NeurIPS},
  year         = {2024},

}

@article{RMT-R,
  title={In Search of Needles in a 10M Haystack: Recurrent Memory Finds What LLMs Miss},
  author={Kuratov, Yuri and Bulatov, Aydar and others},
  journal={arXiv:2402.10790},
  year={2024}
}

@inproceedings{DBLP:conf/kbse/LiL000J21,
  author       = {Jia Li and
                  Yongmin Li and
                  Ge Li and others},
  title        = {EditSum: {A} Retrieve-and-Edit Framework for Source Code Summarization},
  booktitle    = {ASE},
  year         = {2021}
}

@inproceedings{DBLP:conf/icsm/YuYCLZ22,
  author       = {Chi Yu and
                  Guang Yang and
                  Xiang Chen and others},
  title        = {BashExplainer: Retrieval-Augmented Bash Code Comment Generation based on Fine-tuned CodeBERT},
  booktitle    = {ICSME},
  year         = {2022}
}

@inproceedings{DBLP:conf/nips/HashimotoGOL18,
  author       = {Tatsunori B. Hashimoto and
                  Kelvin Guu and
                  Yonatan Oren and
                  Percy Liang},
  title        = {A Retrieve-and-Edit Framework for Predicting Structured Outputs},
  booktitle    = {NeurIPS},
  year         = {2018}
}

@inproceedings{DBLP:conf/kbse/WeiLLXJ20,
  author       = {Bolin Wei and
                  Yongmin Li and
                  Ge Li and others},
  title        = {Retrieve and Refine: Exemplar-based Neural Comment Generation},
  booktitle    = {ASE},
  year         = {2020}
}

@inproceedings{DBLP:conf/emnlp/ShiW0DZHZ022,
  author       = {Ensheng Shi and
                  Yanlin Wang and
                  Wei Tao and others},
  title        = {{RACE:} Retrieval-augmented Commit Message Generation},
  booktitle    = {EMNLP},
  year         = {2022}
}

@inproceedings{chen2022re,
  title={Re-imagen: Retrieval-augmented text-to-image generator},
  author={Chen, Wenhu and Hu, Hexiang and Saharia, Chitwan and Cohen, William W},
  booktitle={ICLR},
  year={2023}
}

@inproceedings{sheynin2022knn,
  title={Knn-diffusion: Image generation via large-scale retrieval},
  author={Sheynin, Shelly and Ashual, Oron and Polyak, Adam and others},
  booktitle={ICLR},
  year={2023}
}

@inproceedings{blattmann2022retrieval,
  title={Retrieval-augmented diffusion models},
  author={Blattmann, Andreas and Rombach, Robin and Oktay, Kaan and others},
  booktitle={NeurIPS},
  year={2022}
}

@article{rombach2022text,
  title={Text-guided synthesis of artistic images with retrieval-augmented diffusion models},
  author={Rombach, Robin and Blattmann, Andreas and Ommer, Bj{\"o}rn},
  journal={arXiv:2207.13038},
  year={2022}
}

@article{li2022memory,
  title={Memory-driven text-to-image generation},
  author={Li, Bowen and Torr, Philip HS and Lukasiewicz, Thomas},
  journal={arXiv:2208.07022},
  year={2022}
}

@inproceedings{DBLP:conf/naacl/OguzCKPOSGMY22,
  author       = {Barlas Oguz and
                  Xilun Chen and
                  Vladimir Karpukhin and others},
  title        = {UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering},
  booktitle    = {NAACL Findings},
  year         = {2022}
}

@inproceedings{DBLP:conf/iclr/YuZNZL0HWWX23,
  author       = {Donghan Yu and
                  Sheng Zhang and others},
  title        = {DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases},
  booktitle    = {ICLR},
  year         = {2023}
}

@inproceedings{DBLP:conf/cikm/DongLWZXX23,
  author       = {Guanting Dong and
                  Rumei Li and
                  Sirui Wang and others},
  title        = {Bridging the KB-Text Gap: Leveraging Structured Knowledge-aware Pre-training for {KBQA}},
  booktitle    = {CIKM},
  year         = {2023}
}

@article{DBLP:journals/corr/abs-2308-13259,
  author       = {Keheng Wang and
                  Feiyu Duan and
                  Sirui Wang and others},
  title        = {Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answering},
  journal      = {arXiv:2308.13259},
  year         = {2023}
}

@inproceedings{DBLP:conf/sigir/YuY23,
  author       = {Donghan Yu and
                  Yiming Yang},
  title        = {Retrieval-Enhanced Generative Model for Large-Scale Knowledge Graph Completion},
  booktitle    = {SIGIR},
  year         = {2023}
}

@inproceedings{TOME,
  title={Mention Memory: incorporating textual knowledge into Transformers through entity mention attention},
  author={de Jong, Michiel and Zemlyanskiy, Yury and FitzGerald, Nicholas and others},
  booktitle={ICLR},
  year={2021}
}

@inproceedings{EaE,
  title={Entities as Experts: Sparse Memory Access with Entity Supervision},
  author={F{\'e}vry, Thibault and Soares, Livio Baldini and others},
  booktitle={EMNLP},
  year={2020}
}

@inproceedings{jing2023amd,
  title={Amd: Anatomical motion diffusion with interpretable motion decomposition and fusion},
  author={Jing, Beibei and Zhang, Youjia and Song, Zikai and others},
  booktitle={AAAI},
  year={2024}
}

@inproceedings{DBLP:journals/corr/abs-2309-08051,
  title={Retrieval-augmented text-to-audio generation},
  author={Yuan, Yi and Liu, Haohe and Liu, Xubo and others},
  booktitle={ICASSP},
  year={2024}
}

@article{DBLP:journals/tip/YangCZ23,
  author       = {Bang Yang and
                  Meng Cao and
                  Yuexian Zou},
  title        = {Concept-Aware Video Captioning: Describing Videos With Effective Prior
                  Information},
  journal      = {TIP},
  volume       = {32},
  pages        = {5366--5378},
  year         = {2023},
}

@inproceedings{TRIME,
  author       = {Zexuan Zhong and
                  Tao Lei and
                  Danqi Chen},
  title        = {Training Language Models with Memory Augmentation},
  booktitle    = {EMNLP},
  year         = {2022}
}

@inproceedings{NPM,
  author       = {Sewon Min and
                  Weijia Shi and
                  Mike Lewis and others},
  title        = {Nonparametric Masked Language Modeling},
  booktitle    = {ACL Findings},
  year         = {2023}
}

@inproceedings{DBLP:conf/emnlp/Zhang0YC23,
  author       = {Xiangyu Zhang and
                  Yu Zhou and
                  Guang Yang and
                  Taolue Chen},
  title        = {Syntax-Aware Retrieval Augmented Code Generation},
  booktitle    = {EMNLP Findings},
  year         = {2023}
}

@inproceedings{fei2021memory,
  title={Memory-augmented image captioning},
  author={Fei, Zhengcong},
  booktitle={AAAI},
  year={2021}
}

@inproceedings{Speculative_Decoding,
  author       = {Yaniv Leviathan and
                  Matan Kalman and
                  Yossi Matias},
  title        = {Fast Inference from Transformers via Speculative Decoding},
  booktitle    = {{ICML}},
  year         = {2023}
}

@inproceedings{COG,
  author       = {Tian Lan and
                  Deng Cai and
                  Yan Wang and others},
  title        = {Copy is All You Need},
  booktitle    = {ICLR},
  year         = {2023}
}

@article{RetrievalisAccurateGeneration,
  title={Retrieval is Accurate Generation},
  author={Cao, Bowen and Cai, Deng and Cui, Leyang and others},
  journal={arXiv:2402.17532},
  year={2024}
}

@inproceedings{Query2doc,
  author       = {Liang Wang and
                  Nan Yang and
                  Furu Wei},
  title        = {Query2doc: Query Expansion with Large Language Models},
  booktitle    = {EMNLP},
  year         = {2023}
}

@inproceedings{HyDE,
  author       = {Luyu Gao and
                  Xueguang Ma and
                  Jimmy Lin and
                  Jamie Callan},
  title        = {Precise Zero-Shot Dense Retrieval without Relevance Labels},
  booktitle    = {ACL},
  year         = {2023}
}

@inproceedings{TOC,
  title={Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Models},
  author={Kim, Gangwoo and Kim, Sungdong and Jeon, Byeongguk and others},
  booktitle={EMNLP},
  year={2023}
}

@article{RQ-RAG,
  title={RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation},
  author={Chan, Chi-Min and Xu, Chunpu and others},
  journal={arXiv:2404.00610},
  year={2024}
}

@inproceedings{tayal2024dynamic,
  title={Dynamic Contexts for Generating Suggestion Questions in RAG Based Conversational Systems},
  author={Tayal, Anuja and Tyagi, Aman},
  booktitle={WWW’24 Companion},
  year={2024}
}

@article{LESS,
  author       = {Mengzhou Xia and
                  Sadhika Malladi and
                  Suchin Gururangan and others},
  title        = {{LESS:} Selecting Influential Data for Targeted Instruction Tuning},
  journal      = {arXiv:2402.04333},
  year         = {2024}
}

@article{Telco-RAG,
  title={Telco-RAG: Navigating the challenges of retrieval-augmented language models for telecommunications},
  author={Bornea, Andrei-Laurentiu and Ayed, Fadhel and others},
  journal={arXiv:2404.15939},
  year={2024}
}

@inproceedings{ReAct,
  author       = {Shunyu Yao and
                  Jeffrey Zhao and
                  Dian Yu and others},
  title        = {ReAct: Synergizing Reasoning and Acting in Language Models},
  booktitle    = {{ICLR}},
  year         = {2023}
}

@inproceedings{COT,
  author       = {Jason Wei and
                  Xuezhi Wang and
                  Dale Schuurmans and others},
  title        = {Chain-of-Thought Prompting Elicits Reasoning in Large Language Models},
  booktitle    = {NeurIPS},
  year         = {2022}
}

@article{RATP,
  title={Retrieval-Augmented Thought Process as Sequential Decision Making},
  author={Pouplin, Thomas and Sun, Hao and Holt, Samuel and Van der Schaar, Mihaela},
  journal={arXiv:2402.07812},
  year={2024}
}

@software{LlamaIndex,
author = {Liu, Jerry},
month = {11},
title = {{LlamaIndex}},
url = {https://github.com/jerryjliu/llama_index},
year = {2022}
}

@inproceedings{RAPTOR,
  title={RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval},
  author={Sarthi, Parth and Abdullah, Salman and Tuli, Aditi and others},
  booktitle={ICLR},
  year={2023}
}

@article{Prompt-RAG,
  title={Prompt-RAG: Pioneering Vector Embedding-Free Retrieval-Augmented Generation in Niche Domains, Exemplified by Korean Medicine},
  author={Kang, Bongsu and Kim, Jundong and others},
  journal={arXiv:2401.11246},
  year={2024}
}

@article{raina2024question,
  title={Question-Based Retrieval using Atomic Units for Enterprise RAG},
  author={Raina, Vatsal and others},
  journal={arXiv:2405.12363},
  year={2024}
}

@article{bge_embedding,
      author={Shitao Xiao and Zheng Liu and Peitian Zhang and others},
      title={C-Pack: Packaged Resources To Advance General Chinese Embedding}, 
      journal={arxiv:2309.07597},
      year={2023}
}

@article{bge_m3,
  author={Chen, Jianlv and Xiao, Shitao and Zhang, Peitian and others},
  title={BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation},
  journal      = {arxiv:2309.07597},
  year={2023}
}

@article{cocktail,
      author={Shitao Xiao and Zheng Liu and Peitian Zhang and Xingrun Xing},
      title={LM-Cocktail: Resilient Tuning of Language Models via Model Merging}, 
      journal={arxiv:2311.13534},
      year={2023}
}

@article{llm_embedder,
      author={Peitian Zhang and Shitao Xiao and Zheng Liu and Zhicheng Dou and Jian-Yun Nie},
      title={Retrieve Anything To Augment Large Language Models}, 
      journal={arxiv:2310.07554},
      year={2023}
}

@article{RL4RAG,
  author       = {Mandar Kulkarni and
                  Praveen Tangarajan and
                  Kyung Kim and others},
  title        = {Reinforcement Learning for Optimizing {RAG} for Domain Chatbots},
  journal      = {arXiv:2401.06800},
  year         = {2024}
}

@inproceedings{DBLP:conf/sigsoft/Wang0JH23,
  author       = {Weishi Wang and
                  Yue Wang and others},
  title        = {RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair},
  booktitle    = {ESEC/FSE},
  year         = {2023}
}

@article{Blended-RAG,
  title={Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers},
  author={Sawarkar, Kunal and Mangal, Abhilasha and others},
  journal={arXiv:2404.07220},
  year={2024}
}

@article{CRAG,
  title={Corrective Retrieval Augmented Generation},
  author={Yan, Shi-Qi and Gu, Jia-Chen and Zhu, Yun and Ling, Zhen-Hua},
  journal={arXiv:2401.15884},
  year={2024}
}

@inproceedings{RAGAE,
  author={Huang, Wenyu and Lapata, Mirella and Vougiouklis, Pavlos and others},
  title={Retrieval Augmented Generation with Rich Answer Encoding},
  booktitle={IJCNLP-AACL},
  year={2023}
}

@article{UniMS-RAG,
  author       = {Hongru Wang and
                  Wenyu Huang and
                  Yang Deng and others},
  title        = {UniMS-RAG: {A} Unified Multi-source Retrieval-Augmented Generation
                  for Personalized Dialogue Systems},
  journal      = {arXiv:2401.13256},
  year         = {2024}
}

@inproceedings{koley2024you,
  title={You'll Never Walk Alone: A Sketch and Text Duet for Fine-Grained Image Retrieval},
  author={Koley, Subhadeep and Bhunia, Ayan Kumar and others},
  booktitle={CVPR},
  year={2024}
}

@inproceedings{Re2G,
  author       = {Michael R. Glass and
                  Gaetano Rossiello and
                  Md. Faisal Mahbub Chowdhury and others},
  title        = {Re2G: Retrieve, Rerank, Generate},
  booktitle    = {{NAACL}},
  year         = {2022}
}

@article{ReRanker,
  author       = {Rodrigo Frassetto Nogueira and
                  Kyunghyun Cho},
  title        = {Passage Re-ranking with {BERT}},
  journal      = {arxiv:1901.04085},
  year         = {2019}
}

@article{li2023acecoder,
  title={AceCoder: Utilizing Existing Code to Enhance Code Generation},
  author={Li, Jia and Zhao, Yunfei and Li, Yongmin and others},
  journal={arXiv:2303.17780},
  year={2023}
}

@inproceedings{DBLP:conf/emnlp/0010Z0L22,
  author       = {Peng Shi and
                  Rui Zhang and
                  He Bai and
                  Jimmy Lin},
  title        = {{XRICL:} Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic Parsing},
  booktitle    = {EMNLP Findings},
  year         = {2022}
}

@article{rangan2024fine,
  title={A Fine-tuning Enhanced RAG System with Quantized Influence Measure as AI Judge},
  author={Rangan, Keshav and Yin, Yiqiao},
  journal={ arXiv:2402.17081},
  year={2024}
}

@inproceedings{UDAPDR,
  title={UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankers},
  author={Saad-Falcon, Jon and Khattab, Omar and Santhanam, Keshav and others},
  booktitle={EMNLP},
  year={2023}
}

@article{LLM-R,
  title={Learning to retrieve in-context examples for large language models},
  author={Wang, Liang and Yang, Nan and Wei, Furu},
  journal={arXiv:2307.07164},
  year={2023}
}

@article{finardi2024chronicles,
  title={The Chronicles of RAG: The Retriever, the Chunk and the Generator},
  author={Finardi, Paulo and Avila, Leonardo and others},
  journal={arXiv:2401.07883},
  year={2024}
}

@article{li2024enhancing,
  title={Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases},
  author={Li, Jiarui and Yuan, Ye and Zhang, Zehua},
  journal={arXiv:2403.10446},
  year={2024}
}

@article{FILCO,
  author       = {Zhiruo Wang and
                  Jun Araki and
                  Zhengbao Jiang and others},
  title        = {Learning to Filter Context for Retrieval-Augmented Generation},
  journal      = {arxiv:2311.08377},
  year         = {2023}
}

@inproceedings{FiD-Light,
  author       = {Sebastian Hofst{\"{a}}tter and
                  Jiecao Chen and
                  Karthik Raman and
                  Hamed Zamani},
  title        = {FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation},
  booktitle    = {{SIGIR}},
  year         = {2023}
}

@article{RRR,
  author       = {Daman Arora and
                  Anush Kini and
                  Sayak Ray Chowdhury and others},
  title        = {GAR-meets-RAG Paradigm for Zero-Shot Information Retrieval},
  journal      = {arXiv:2310.20158},
  year         = {2023}
}

@misc{Pinecone,
    howpublished = {\url{https://www.pinecone.io}},
}
@misc{TurLens,
    howpublished = {\url{https://github.com/truera/trulens}},
}

@article{GENREAD,
  title={Generate rather than retrieve: Large language models are strong context generators},
  author={Yu, Wenhao and Iter, Dan and others},
  journal={arXiv:2209.10063},
  year={2022}
}

@article{GRG,
  title={Generator-retriever-generator: A novel approach to open-domain question answering},
  author={Abdallah, Abdelrahman and Jatowt, Adam},
  journal={arXiv:2307.11278},
  year={2023}
}

@article{Multi-Head-RAG,
  title={Multi-Head RAG: Solving Multi-Aspect Problems with LLMs},
  author={Besta, Maciej and Kubicek, Ales and others},
  journal={arXiv:2406.05085},
  year={2024}
}

@article{Prompt_Engineering_Guide,
author = {Saravia, Elvis},
journal = {https://github.com/dair-ai/Prompt-Engineering-Guide},
month = {12},
title = {{Prompt Engineering Guide}},
year = {2022}
}

@article{StepBack-Prompting,
  author       = {Huaixiu Steven Zheng and
                  Swaroop Mishra and others},
  title        = {Take a Step Back: Evoking Reasoning via Abstraction in Large Language
                  Models},
  journal      = {arxiv:2310.06117},
  year         = {2023}
}

@article{active-prompt,
  author       = {Shizhe Diao and
                  Pengcheng Wang and
                  Yong Lin and
                  Tong Zhang},
  title        = {Active Prompting with Chain-of-Thought for Large Language Models},
  journal      = {arxiv:2302.12246},
  year         = {2023}
}

@inproceedings{LLMLingua,
  author       = {Huiqiang Jiang and
                  Qianhui Wu and
                  Chin{-}Yew Lin and others},
  title        = {LLMLingua: Compressing Prompts for Accelerated Inference of Large
                  Language Models},
  booktitle    = {{EMNLP}},
  year         = {2023}
}

@article{Lost_in_the_middle,
  author       = {Nelson F. Liu and
                  Kevin Lin and
                  John Hewitt and others},
  title        = {Lost in the Middle: How Language Models Use Long Contexts},
  journal      = {arxiv:2307.03172},
  year         = {2023}
}

@article{ahmed2024automatic,
      title={Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)}, 
      author={Toufique Ahmed and Kunal Suresh Pai and Premkumar Devanbu and Earl T. Barr},
      year={2024},
      journal={arXiv:2304.06815}
}

@article{ActiveRAG,
  title={ActiveRAG: Revealing the Treasures of Knowledge via Active Learning},
  author={Xu, Zhipeng and Liu, Zhenghao and Liu, Yibin and others},
  journal={arXiv:2402.13547},
  year={2024}
}

@article{CODEGEN-MONO,
  author       = {Erik Nijkamp and
                  Bo Pang and
                  Hiroaki Hayashi and others},
  title        = {A Conversational Paradigm for Program Synthesis},
  journal      = {arxiv:2203.13474},
  year         = {2022}
}

@article{DBLP:journals/corr/abs-2307-06940,
  title={Animate-a-story: Storytelling with retrieval-augmented video generation},
  author={He, Yingqing and Xia, Menghan and Chen, Haoxin and others},
  journal={arXiv:2307.06940},
  year={2023}
}

@inproceedings{LoRA,
  author       = {Edward J. Hu and
                  Yelong Shen and
                  Phillip Wallis and others},
  title        = {LoRA: Low-Rank Adaptation of Large Language Models},
  booktitle    = {{ICLR}},
  year         = {2022}
}

@article{DBLP:journals/corr/abs-2306-06490,
  author       = {Changshu Liu and
                  Pelin {\c{C}}etin and
                  Yogesh Patodia and others},
  title        = {Automated Code Editing with Search-Generate-Modify},
  journal      = {arXiv:2306.06490},
  year         = {2023}
}

@inproceedings{DBLP:conf/aaai/JoshiSG0VR23,
  author       = {Harshit Joshi and
                  Jos{\'{e}} Pablo Cambronero S{\'{a}}nchez and
                  Sumit Gulwani and others},
  title        = {Repair Is Nearly Generation: Multilingual Program Repair with LLMs},
  booktitle    = {AAAI},
  year         = {2023}
}

@article{FLARE,
  title={Active retrieval augmented generation},
  author={Jiang, Zhengbao and Xu, Frank F and Gao, Luyu and others},
  journal={arXiv:2305.06983},
  year={2023}
}

@article{lm-calibration,
  author       = {Zhengbao Jiang and
                  Jun Araki and
                  Haibo Ding and
                  Graham Neubig},
  title        = {How Can We Know \emph{When} Language Models Know? On the Calibration
                  of Language Models for Question Answering},
  journal      = {TACL},
  year         = {2021}
}

@inproceedings{LLM_Struggle_to_Learn_Long-Tail_Knowledge,
  author       = {Nikhil Kandpal and
                  Haikang Deng and
                  Adam Roberts and others},
  title        = {Large Language Models Struggle to Learn Long-Tail Knowledge},
  booktitle    = {ICML},
  year         = {2023}
}

@article{LLM-Knowledge-Boundary,
  author       = {Ruiyang Ren and
                  Yuhao Wang and
                  Yingqi Qu and others},
  title        = {Investigating the Factual Knowledge Boundary of Large Language Models
                  with Retrieval Augmentation},
  journal      = {arxiv:2307.11019},
  year         = {2023}
}

@inproceedings{SKR,
  author       = {Yile Wang and
                  Peng Li and
                  Maosong Sun and
                  Yang Liu},
  title        = {Self-Knowledge Guided Retrieval Augmentation for Large Language Models},
  booktitle    = {{EMNLP Findings}},
  year         = {2023}
}

@article{Rowen,
  author       = {Hanxing Ding and
                  Liang Pang and
                  Zihao Wei and others},
  title        = {Retrieve Only When It Needs: Adaptive Retrieval Augmentation for Hallucination
                  Mitigation in Large Language Models},
  journal      = {arXiv:2402.10612},
  year         = {2024},
}

@article{AdaptiveRAG,
  title={Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity},
  author={Jeong, Soyeong and Baek, Jinheon and Cho, Sukmin and others},
  journal={arXiv:2403.14403},
  year={2024}
}

@inproceedings{DBLP:conf/emnlp/ZhangCZKLZMLC23,
  author       = {Fengji Zhang and
                  Bei Chen and others},
  title        = {RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation},
  booktitle    = {EMNLP},
  year         = {2023}
}

@inproceedings{ITER-RETGEN,
  author       = {Zhihong Shao and
                  Yeyun Gong and
                  Yelong Shen and others},
  title        = {Enhancing Retrieval-Augmented Large Language Models with Iterative
                  Retrieval-Generation Synergy},
  booktitle    = {EMNLP Findings},
  year         = {2023}
}

@inproceedings{SelfMemory,
  author       = {Xin Cheng and
                  Di Luo and
                  Xiuying Chen and others},
  title        = {Lift Yourself Up: Retrieval-augmented Text Generation with Self-Memory},
  booktitle    = {NeurIPS},
  year         = {2023}
}

@article{RAT,
  title={RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation},
  author={Wang, Zihao and Liu, Anji and Lin, Haowei and others},
  journal={arXiv:2403.05313},
  year={2024}
}

@article{DBLP:journals/corr/abs-2401-05856,
  author       = {Scott Barnett and
                  Stefanus Kurniawan and
                  Srikanth Thudumu and others},
  title        = {Seven Failure Points When Engineering a Retrieval Augmented Generation
                  System},
  journal      = {arXiv:2401.05856},
  year         = {2024}
}

@article{DBLP:journals/corr/abs-2401-14887,
  author       = {Florin Cuconasu and
                  Giovanni Trappolini and
                  Federico Siciliano and others},
  title        = {The Power of Noise: Redefining Retrieval for {RAG} Systems},
  journal      = {arXiv:2401.14887},
  year         = {2024}
}

@article{qiu2022evaluating,
  title={Evaluating the impact of model scale for compositional generalization in semantic parsing},
  author={Qiu, Linlu and Shaw, Peter and Pasupat, Panupong and others},
  journal={arXiv:2205.12253},
  year={2022}
}

@article{Query_Expansion_by_Prompting_LLMs,
  author       = {Rolf Jagerman and
                  Honglei Zhuang and
                  Zhen Qin and others},
  title        = {Query Expansion by Prompting Large Language Models},
  journal      = {arxiv:2305.03653},
  year         = {2023}
}

@article{EA,
  author       = {Hailin Zhang and
                  Penghao Zhao and
                  Xupeng Miao and others},
  title        = {Experimental Analysis of Large-scale Learnable Vector Storage Compression},
  journal      = {{VLDB}},
  year         = {2023}
}

@article{DBLP:journals/corr/abs-2302-05578,
  author       = {Renat Aksitov and
                  Chung{-}Ching Chang and
                  David Reitter and others},
  title        = {Characterizing Attribution and Fluency Tradeoffs for Retrieval-Augmented
                  Large Language Models},
  journal      = {arXiv:2302.05578},
  year         = {2023}
}

@article{DBLP:journals/corr/abs-2308-16137,
  author       = {Chi Han and
                  Qifan Wang and
                  Wenhan Xiong and others},
  title        = {LM-Infinite: Simple On-the-Fly Length Generalization for Large Language
                  Models},
  journal      = {arXiv:2308.16137},
  year         = {2023}
}

@techreport{trajtenberg2018ai,
  title={AI as the next GPT: a Political-Economy Perspective},
  author={Trajtenberg, Manuel},
  year={2018},
  institution={National Bureau of Economic Research}
}

@article{liu2023deid,
  title={Deid-gpt: Zero-shot medical text de-identification by gpt-4},
  author={Liu, Zhengliang and Huang, Yue and Yu, Xiaowei and Zhang, Lu and Wu, Zihao and Cao, Chao and Dai, Haixing and Zhao, Lin and Li, Yiwei and Shu, Peng and others},
  journal={arXiv preprint arXiv:2303.11032},
  year={2023}
}

@article{leippold2023thus,
  title={Thus spoke GPT-3: Interviewing a large-language model on climate finance},
  author={Leippold, Markus},
  journal={Finance Research Letters},
  volume={53},
  pages={103617},
  year={2023},
  publisher={Elsevier}
}

@article{yenduri2024gpt,
  title={Gpt (generative pre-trained transformer)--a comprehensive review on enabling technologies, potential applications, emerging challenges, and future directions},
  author={Yenduri, Gokul and Ramalingam, M and Selvi, G Chemmalar and Supriya, Y and Srivastava, Gautam and Maddikunta, Praveen Kumar Reddy and Raj, G Deepti and Jhaveri, Rutvij H and Prabadevi, B and Wang, Weizheng and others},
  journal={IEEE Access},
  year={2024},
  publisher={IEEE}
}

@article{lewis2020retrieval,
  title={Retrieval-augmented generation for knowledge-intensive nlp tasks},
  author={Lewis, Patrick and Perez, Ethan and Piktus, Aleksandra and Petroni, Fabio and Karpukhin, Vladimir and Goyal, Naman and K{\"u}ttler, Heinrich and Lewis, Mike and Yih, Wen-tau and Rockt{\"a}schel, Tim and others},
  journal={Advances in Neural Information Processing Systems},
  volume={33},
  pages={9459--9474},
  year={2020}
}

@article{lo2023clear,
  title={The CLEAR path: A framework for enhancing information literacy through prompt engineering},
  author={Lo, Leo S},
  journal={The Journal of Academic Librarianship},
  volume={49},
  number={4},
  pages={102720},
  year={2023},
  publisher={Elsevier}
}

@article{hu2021lora,
  title={Lora: Low-rank adaptation of large language models},
  author={Hu, Edward J and Shen, Yelong and Wallis, Phillip and Allen-Zhu, Zeyuan and Li, Yuanzhi and Wang, Shean and Wang, Lu and Chen, Weizhu},
  journal={arXiv preprint arXiv:2106.09685},
  year={2021}
}

@inproceedings{wortsman2022robust,
  title={Robust fine-tuning of zero-shot models},
  author={Wortsman, Mitchell and Ilharco, Gabriel and Kim, Jong Wook and Li, Mike and Kornblith, Simon and Roelofs, Rebecca and Lopes, Raphael Gontijo and Hajishirzi, Hannaneh and Farhadi, Ali and Namkoong, Hongseok and others},
  booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
  pages={7959--7971},
  year={2022}
}

@article{friederich2017fine,
  title={Fine-tuning},
  author={Friederich, Simon},
  journal={The Stanford encyclopedia of philosophy},
  year={2017}
}

@article{white2023prompt,
  title={A prompt pattern catalog to enhance prompt engineering with chatgpt},
  author={White, Jules and Fu, Quchen and Hays, Sam and Sandborn, Michael and Olea, Carlos and Gilbert, Henry and Elnashar, Ashraf and Spencer-Smith, Jesse and Schmidt, Douglas C},
  journal={arXiv preprint arXiv:2302.11382},
  year={2023}
}

@article{sahoo2024systematic,
  title={A systematic survey of prompt engineering in large language models: Techniques and applications},
  author={Sahoo, Pranab and Singh, Ayush Kumar and Saha, Sriparna and Jain, Vinija and Mondal, Samrat and Chadha, Aman},
  journal={arXiv preprint arXiv:2402.07927},
  year={2024}
}

@article{tonmoy2024comprehensive,
  title={A comprehensive survey of hallucination mitigation techniques in large language models},
  author={Tonmoy, SM and Zaman, SM and Jain, Vinija and Rani, Anku and Rawte, Vipula and Chadha, Aman and Das, Amitava},
  journal={arXiv preprint arXiv:2401.01313},
  year={2024}
}

@article{touvron2023llama,
  title={Llama 2: Open foundation and fine-tuned chat models},
  author={Touvron, Hugo and Martin, Louis and Stone, Kevin and Albert, Peter and Almahairi, Amjad and Babaei, Yasmine and Bashlykov, Nikolay and Batra, Soumya and Bhargava, Prajjwal and Bhosale, Shruti and others},
  journal={arXiv preprint arXiv:2307.09288},
  year={2023}
}

@article{chung2024scaling,
  title={Scaling instruction-finetuned language models},
  author={Chung, Hyung Won and Hou, Le and Longpre, Shayne and Zoph, Barret and Tay, Yi and Fedus, William and Li, Yunxuan and Wang, Xuezhi and Dehghani, Mostafa and Brahma, Siddhartha and others},
  journal={Journal of Machine Learning Research},
  volume={25},
  number={70},
  pages={1--53},
  year={2024}
}

@article{dettmers2024qlora,
  title={Qlora: Efficient finetuning of quantized llms},
  author={Dettmers, Tim and Pagnoni, Artidoro and Holtzman, Ari and Zettlemoyer, Luke},
  journal={Advances in Neural Information Processing Systems},
  volume={36},
  year={2024}
}

@misc{brown2020languagemodelsfewshotlearners,
      title={Language Models are Few-Shot Learners},
      author={Tom B. Brown and Benjamin Mann and Nick Ryder and Melanie Subbiah and Jared Kaplan and Prafulla Dhariwal and Arvind Neelakantan and Pranav Shyam and Girish Sastry and Amanda Askell and Sandhini Agarwal and Ariel Herbert-Voss and Gretchen Krueger and Tom Henighan and Rewon Child and Aditya Ramesh and Daniel M. Ziegler and Jeffrey Wu and Clemens Winter and Christopher Hesse and Mark Chen and Eric Sigler and Mateusz Litwin and Scott Gray and Benjamin Chess and Jack Clark and Christopher Berner and Sam McCandlish and Alec Radford and Ilya Sutskever and Dario Amodei},
      year={2020},
      eprint={2005.14165},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2005.14165},
}

@misc{raffel2023exploringlimitstransferlearning,
      title={Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer},
      author={Colin Raffel and Noam Shazeer and Adam Roberts and Katherine Lee and Sharan Narang and Michael Matena and Yanqi Zhou and Wei Li and Peter J. Liu},
      year={2023},
      eprint={1910.10683},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/1910.10683},
}