Elamur Research⌕
☰
home / papers / 2024 / Retrieval-Augmented Generation for Natural Language Processing: A Survey

Retrieval-Augmented Generation for Natural Language Processing: A Survey

Paper · 2024 · Shangyu Wu, Ying Xiong, Yufei Cui et al.

Summary

Large language models store knowledge implicitly in their weights. As a result, they can produce fluent but false answers, they need costly retraining to refresh facts, and they often lack depth in specialised domains. Retrieval-augmented generation (RAG) addresses these issues by consulting an external knowledge base at inference time. This survey describes RAG for NLP as a system with three parts. The first is a retriever, covering chunking, encoding, index and vector database construction, ANN search and post-processing. The second is retrieval fusion, and the third is a generator. The core contribution is a four-way taxonomy of how retrieved material enters the model: query-based, logits-based, latent and parametric fusion. The authors compare these by accessibility, efficiency, implementation effort and use cases, and discuss hybrid designs. They also review RAG across NLP tasks, evaluation methods and benchmark weaknesses, training with and without knowledge-base updates, deployment tooling, and open problems such as security, efficiency and GraphRAG. Being a survey, it reports no new experiments. Its value is a structured map of the field plus runnable tutorial code.

Key points

  • The fusion taxonomy has four types:
    • Query-based: retrieved chunks are concatenated with the input.
    • Logits-based: output logits are ensembled or calibrated.
    • Latent: retrieval representations are injected into the generator's hidden states.
    • Parametric: the top-k relevant LoRA modules are retrieved and merged into the weights.
  • Generators fall into three groups:
    • proprietary models (GPT, Gemini);
    • open-weight models (Mistral, Qwen, DeepSeek, Llama);
    • retrieval-aware architectures (RETRO, Enc-Dec).
  • The survey is positioned against six earlier RAG surveys. According to the authors, it is the only one that ships tutorial code: github.com/luffy06/RAG-Tutorials.
  • Covered tasks include language modeling, machine translation, summarization, question answering, information extraction, text classification and dialogue systems.
  • GraphRAG (Edge et al. 2024; open-source implementation by Microsoft) builds an entity graph with community summaries. The cited analyses (Xiang et al. 2025) show it does not consistently beat plain RAG and carries higher latency and indexing cost.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓McGill UniversityMontreal · Canada87 works · 11,027 citations🎓Mohamed bin Zayed University of Artificial IntelligenceAbu Dhabi · United Arab Emirates124 works · 5,676 citations🎓National Taiwan UniversityTaipei · Taiwan29 works · 2,116 citations🎓City University of Hong KongHong Kong · China45 works · 3,014 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksComputer Vision and Pattern Recognition · 2,869 worksInformation Systems · 1,437 works

🧭 Topics 1Research subjects and languages the work is about.Information retrieval & search · 473 works

Cite

Cite as Shangyu Wu, Ying Xiong, Yufei Cui, Haolun Wu, Can Chen, Ye Yuan, Lianming Huang, Xue Liu, Tei-Wei Kuo, Nan Guan and Chun Jason Xue. 2024. Retrieval-Augmented Generation for Natural Language Processing: A Survey. arXiv:2407.13193.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2407.13193 · arXiv 2407.13193

@misc{wu2024retrieval,
  title = {{Retrieval-Augmented Generation for Natural Language Processing: A Survey}},
  author = {Shangyu Wu, Ying Xiong, Yufei Cui, Haolun Wu, Can Chen, Ye Yuan, Lianming Huang, Xue Liu, Tei-Wei Kuo, Nan Guan and Chun Jason Xue},
  year = {2024},
  doi = {10.48550/arxiv.2407.13193},
  eprint = {2407.13193},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2407.13193}
}

References

276 references, 88 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. (2025a) Llm01:2025 prompt injection - owasp gen ai security project. URL https://genai.owasp.org/llmrisk/llm01-prompt-injection/ (2025b) Llm08:2025 vector and embedding weaknesses -owasp gen ai security project. URL https://genai.owasp.org/llmrisk/ llm082025-vector-and-embedding-weaknesses/ Abdalla… — [arXiv:2601.09523](https://arxiv.org/abs/2601.09523) ↗
  2. Abnar S, Dehghani M, Neyshabur B, et al (2022) Exploring the limits of large scale pre-training. In: Proceedings of The Tenth International Conference on Learning Representations (ICLR) find
  3. Ainslie J, Lee-Thorp J, de Jong M, et al (2023) GQA: training generalized multi-query transformer models from multi-head checkpoints. In: Bouamor H, Pino J, Bali K (eds) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 4895–4901
  4. AlKhamissi B, Li M, Celikyilmaz A, et al (2022) A review on language models as knowledge bases. CoRR abs/2204.06031 find
  5. Amazon Web Services (2026) Retrieving information from data sources using amazon bedrock knowledge bases. https://docs.aws.amazon.com/bedrock/latest/userguide/ kb-how-retrieval.html, accessed: 2026-03-04 ↗
  6. Anil R, Borgeaud S, Wu Y, et al (2023) Gemini: A family of highly capable multimodal models. CoRR abs/2312.11805
  7. Arefeen MA, Debnath B, Chakradhar S (2024) Leancontext: Cost-efficient domain-specific question answering using llms. Natural Language Processing Journal 7:100065. https://doi.org/10.1016/J.NLP.2024.100065 — [doi:10.1016/j.nlp.2024.100065](https://doi.org/10.1016/j.nlp.2024.100065) ↗
  8. Asai A, Wu Z, Wang Y, et al (2024) Self-rag: Learning to retrieve, generate, and critique through self-reflection. In: Proceedings of The Twelfth International Conference on Learning Representations (ICLR)
  9. Baek J, Aji AF, Saffari A (2023) Knowledge-augmented language model prompting for zero-shot knowledge graph question answering. CoRR abs/2306.04136
  10. Bai H, Zhang W, Hou L, et al (2021) Binarybert: Pushing the limit of BERT quantization. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL/IJCNLP), pp 4334–4348
  11. Bertsch A, Alon U, Neubig G, et al (2023) Unlimiformer: Long-range transformers with unlimited length input. In: Advances in Neural Information Processing Systems 36 (NeurIPS) find
  12. Borgeaud S, Mensch A, Hoffmann J, et al (2022) Improving language models by retrieving from trillions of tokens. In: Proceedings of the 39th International Conference on Machine Learning (ICML), pp 2206–2240 find
  13. Brown TB, Mann B, Ryder N, et al (2020) Language models are few-shot learners. In: Advances in Neural Information Processing Systems 33 (NeurIPS)
  14. Cai D, Wang Y, Li H, et al (2021) Neural machine translation with monolingual translation memory. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL/IJCNLP), pp 7307–7318 find
  15. Castelli V, Chakravarti R, Dana S, et al (2020) The techqa dataset. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL), pp 1269–1278 find
  16. Chalkidis I, Fergadiotis M, Malakasiotis P, et al (2020) LEGAL-BERT: the muppets straight out of law school. In: Findings of the Association for Computational Linguistics: EMNLP, pp 2898–2904
  17. Chang Z, Li M, Jia X, et al (2025) One shot dominance: Knowledge poisoning attack on retrieval-augmented generation systems. In: Findings of the Association for Computational Linguistics: EMNLP, pp 18811–18825 find
  18. Chen J, Chen Q, Li D, et al (2022a) Sedr: Segment representation learning for long documents dense retrieval. CoRR abs/2211.10841 find
  19. Chen J, Lin H, Han X, et al (2024) Benchmarking large language models in retrieval-augmented generation. In: Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI), pp 17754–17762
  20. Chen W, Wang X, Wang WY (2021) A dataset for answering time-sensitive questions. In: Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS Datasets and Benchmarks) find
  21. Chen X, Li L, Zhang N, et al (2022b) Decoupling knowledge from memorization: Retrieval-augmented prompt learning. In: Advances in Neural Information Processing Systems 35 (NeurIPS) find
  22. Chen Y, Li H, Sui Y, et al (2025a) Can indirect prompt injection attacks be detected and removed? In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL), pp 18189–18206
  23. Chen Y, Wang Y, Zhang H, et al (2025b) Fine-grained privacy extraction from retrieval-augmented generation systems via knowledge asymmetry exploitation. CoRR abs/2507.23229 — [arXiv:2507.23229](https://arxiv.org/abs/2507.23229) find
  24. Chen Y, Xiong Y, Wu S, et al (2025c) Beyond semantic similarity: Reducing unnecessary API calls via behavior-aligned retriever. CoRR abs/2508.14323. https://doi.org/10.48550/ARXIV.2508.14323 — [doi:10.48550/arxiv.2508.14323](https://doi.org/10.48550/arxiv.2508.14323) ↗
  25. Chen Y, Xiong Y, Wu S, et al (2026) Refilter: Improving robustness of retrieval-augmented generation via gated filter. arXiv preprint arXiv:260212709 find
  26. Cheng Q, Li X, Li S, et al (2024) Unified active retrieval for retrieval augmented generation. In: Findings of the Association for Computational Linguistics: EMNLP, pp 17153–17166, https://doi.org/10.18653/V1/2024.FINDINGS-EMNLP.999 ↗
  27. Cheng X, Lin Y, Chen X, et al (2023a) Decouple knowledge from paramters for plug-and-play language modeling. In: Findings of the Association for Computational Linguistics: ACL, pp 14288–14308 find
  28. Cheng X, Luo D, Chen X, et al (2023b) Lift yourself up: Retrieval-augmented text generation with self-memory. In: Advances in Neural Information Processing Systems 36 (NeurIPS)
  29. Chevalier A, Wettig A, Ajith A, et al (2023) Adapting language models to compress contexts. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 3829–3846, https://doi.org/10.18653/V1/2023. EMNLP-MAIN.232 ↗
  30. Chuang Y, Fang W, Li S, et al (2023) Expand, rerank, and retrieve: Query reranking for open-domain question answering. In: Findings of the Association for Computational Linguistics: ACL, pp 12131–12147 find
  31. Clark K, Luong M, Le QV, et al (2020) ELECTRA: pre-training text encoders as discriminators rather than generators. In: Proceedings of the 8th International Conference on Learning Representations (ICLR). find
  32. OpenReview.net Cohen S, Bitton R, Nassi B (2024) Unleashing worms and extracting data: Escalating the outcome of attacks against rag-based inference in scale and severity using jailbreaking. CoRR abs/2409.08045 — [arXiv:2409.08045](https://arxiv.org/abs/2409.08045) find
  33. Colombo P, Pires TP, Boudiaf M, et al (2024) Saullm-7b: A pioneering large language model for law. CoRR abs/2403.03883 find
  34. Cui Y, Liu Z, Chen Y, et al (2023) Retrieval-augmented multiple instance learning. In: Advances in Neural Information Processing Systems 36 (NeurIPS) find
  35. Dai Y, Zhang Z, Liu Q, et al (2023) Simple and scalable nearest neighbor machine translation. In: Proceedings of The Eleventh International Conference on Learning Representations (ICLR) find
  36. Dale D, Voita E, Barrault L, et al (2023) Detecting and mitigating hallucinations in machine translation: Model internal workings alone do well, sentence similarity even better. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), pp 36–50
  37. Databricks (2025a) Mosaic ai vector search. https://docs.databricks.com/gcp/en/ vector-search/vector-search, accessed: 2026-03-04 ↗
  38. Databricks (2025b) Vector search retrieval quality guide. URL https://docs.databricks.com/aws/en/vector-search/vector-search-retrieval-quality DeepSeek-AI (2025) Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. CoRR abs/2501.12948 deepset (2026) Haystack documenta… ↗
  39. Deguchi H, Watanabe T, Matsui Y, et al (2023) Subset retrieval nearest neighbor machine translation. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), pp 174–189 find
  40. Dettmers T, Pagnoni A, Holtzman A, et al (2023) Qlora: Efficient finetuning of quantized llms. In: Advances in Neural Information Processing Systems 36 (NeurIPS)
  41. Devlin J, Chang M, Lee K, et al (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), pp 4171–4186
  42. Ding Y, Fan W, Ning L, et al (2024) A survey on RAG meets llms: Towards retrieval-augmented large language models. CoRR abs/2405.06211
  43. Ding Z, Jiang G, Zhang S, et al (2023) SKDBERT: compressing BERT via stochastic knowledge distillation. In: Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI), pp 7414–7422 find
  44. Doostmohammadi E, Norlund T, Kuhlmann M, et al (2023) Surface-based retrieval reduces perplexity of retrieval-augmented language models. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), pp 521–529, https://doi.org/10.18653/V1/2023.ACL-SHORT.45 ↗
  45. Douze M, Guzhva A, Deng C, et al (2024) The faiss library. CoRR abs/2401.08281
  46. DSPy (2026) Tutorial: Retrieval-augmented generation (rag) – dspy. https://dspy.ai/ tutorials/rag/, accessed: 2026-03-04 ↗
  47. Dubois Y, Galambosi B, Liang P, et al (2024) Length-controlled alpacaeval: A simple way to debias automatic evaluators. CoRR abs/2404.04475 find
  48. Edge D, Trinh H, Cheng N, et al (2024) From local to global: A graph RAG approach to query-focused summarization. CoRR abs/2404.16130 find
  49. ES S, James J, Anke LE, et al (2024) Ragas: Automated evaluation of retrieval augmented generation. In: Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL), pp 150–158 explosion (2016) Spacy. misc, URL https://spacy.io/ ↗
  50. Fabbri AR, Ng P, Wang Z, et al (2020) Template-based question generation from retrieved sentences for improved unsupervised question answering. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL), pp 4508–4513 find
  51. Fabbri AR, Kryscinski W, McCann B, et al (2021) Summeval: Re-evaluating summarization evaluation. Transactions of the Association for Computational Linguistics 9:391–409 find
  52. Facebook (2013) RocksDB. Software, URL https://github.com/facebook/rocksdb ↗
  53. Fan A, Gardent C (2022) Generating full length wikipedia biographies: The impact of gender bias on the retrieval-based generation of women biographies. CoRR abs/2204.05879 — [arXiv:2204.05879](https://arxiv.org/abs/2204.05879) find
  54. Fan A, Gardent C, Braud C, et al (2021) Augmenting transformers with knn-based composite memory for dialog. Transactions of the Association for Computational Linguistics 9:82–99
  55. Févry T, Soares LB, FitzGerald N, et al (2020) Entities as experts: Sparse memory access with entity supervision. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 4937–4951
  56. Friel R, Belyi M, Sanyal A (2024) Ragbench: Explainable benchmark for retrieval-augmented generation systems. CoRR abs/2407.11005 — [arXiv:2407.11005](https://arxiv.org/abs/2407.11005) find
  57. Fu Y, Chen C, Chen X, et al (2024) Optimizing the number of clusters for billion-scale quantization-based nearest neighbor search. IEEE Transactions on Knowledge and Data Engineering 36(11):6786–6800 find
  58. Ganesh P, Chen Y, Lou X, et al (2021) Compressing large-scale transformer-based models: A case study on BERT. Transactions of the Association for Computational Linguistics 9:1061–1080
  59. Gao L, Dai Z, Pasupat P, et al (2023a) RARR: researching and revising what language models say, using language models. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), pp 16477–16508, https://doi.org/10.18653/V1/2023.ACL-LONG.910 ↗
  60. Gao T, Yao X, Chen D (2021) Simcse: Simple contrastive learning of sentence embeddings. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 6894–6910
  61. Gao Y, Xiong Y, Gao X, et al (2023b) Retrieval-augmented generation for large language models: A survey. CoRR abs/2312.10997
  62. Glass MR, Wu X, Naik AR, et al (2023) Retrieval-based transformer for table augmentation. In: Findings of the Association for Computational Linguistics: ACL, pp 5635–5648 find
  63. Gong H, Shen Y, Yu D, et al (2020) Recurrent chunking mechanisms for long-text machine reading comprehension. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL), pp 6751–6761 find
  64. Google Cloud (2026a) Use data ingestion with vertex ai rag engine. https://docs.cloud.google.com/vertex-ai/generative-ai/docs/rag-engine/use-data-ingestion, accessed: 2026-03-04 ↗
  65. Google Cloud (2026b) Vertex ai rag engine billing. https://docs.cloud.google.com/ vertex-ai/generative-ai/docs/rag-engine/rag-engine-billing, accessed: 2026-03-04 ↗
  66. Gunawardana A, Shani G (2009) A survey of accuracy evaluation metrics of recommendation tasks. Journal of Machine Learning Research 10:2935–2962 find
  67. Guo D, Tang D, Duan N, et al (2019) Coupling retrieval and meta-learning for context-dependent semantic parsing. In: Proceedings of the 57th Conference of the Association for Computational Linguistics (ACL), pp 855–866 find
  68. Guo R, Sun P, Lindgren E, et al (2020) Accelerating large-scale inference with anisotropic vector quantization. In: Proceedings of the 37th International Conference on Machine Learning (ICML), pp 3887–3896 find
  69. Guo R, Luan X, Xiang L, et al (2022) Manu: A cloud native vector database management system. Proceedings of the VLDB Endowment 15(12):3548–3561 find
  70. Guo Z, Cheng S, Wang Y, et al (2023) Prompt-guided retrieval augmentation for non-knowledge-intensive tasks. In: Findings of the Association for Computational Linguistics: ACL, pp 10896–10912 find
  71. Guu K, Lee K, Tung Z, et al (2020) Retrieval augmented language model pre-training. In: Proceedings of the 37th International Conference on Machine Learning (ICML), pp 3929–3938
  72. Harris D, Harris S (2010) Digital design and computer architecture. find
  73. Morgan Kaufmann Harris ZS (1954) Distributional structure. Word 10(2-3):146–162 find
  74. Hatalis K, Christou D, Myers J, et al (2023) Memory matters: The need to improve long-term memory in llm-agents. In: Proceedings of the AAAI Symposium Series, pp 277–280 find
  75. He Q, Wang Y, Wang W (2024) Can language models act as knowledge bases at scale? CoRR abs/2402.14273 — [arXiv:2402.14273](https://arxiv.org/abs/2402.14273) find
  76. Hoffmann J, Borgeaud S, Mensch A, et al (2022) Training compute-optimal large language models. CoRR abs/2203.15556
  77. Hofstätter S, Chen J, Raman K, et al (2023) Fid-light: Efficient and effective retrieval-augmented text generation. In: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR). ACM, pp 1437–1447 find
  78. Holtzman A, Buys J, Du L, et al (2020) The curious case of neural text degeneration. In: Proceedings of the 8th International Conference on Learning Representations (ICLR)
  79. Hoshi Y, Miyashita D, Ng Y, et al (2023) Ralle: A framework for developing and evaluating retrieval-augmented large language models. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 52–69 find
  80. Hossain N, Ghazvininejad M, Zettlemoyer L (2020) Simple and effective retrieve-edit-rerank text generation. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL), pp 2532–2538, https://doi.org/ 10.18653/V1/2020.ACL-MAIN.228 find
  81. Hu EJ, Shen Y, Wallis P, et al (2022) Lora: Low-rank adaptation of large language models. In: Proceedings of The Tenth International Conference on Learning Representations (ICLR)
  82. Hu W, Gu J, Dou Z, et al (2025a) Mrag-bench: Vision-centric evaluation for retrieval-augmented multimodal models. In: Proceedings of The Thirteenth International Conference on Learning Representations (ICLR) find
  83. Hu X (2023) Multimodal named entity recognition and relation extraction with retrieval-augmented strategy. In: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR). ACM, p 3488 find
  84. Hu Y, Lu Y (2024) RAG and RAU: A survey on retrieval-augmented language model in natural language processing. CoRR abs/2404.19543 — [arXiv:2404.19543](https://arxiv.org/abs/2404.19543) find
  85. Hu Z, Murthy V, Pan Z, et al (2025b) Hedrarag: Coordinating LLM generation and database retrieval in heterogeneous RAG serving. CoRR abs/2507.09138 find
  86. Huang J, Ping W, Xu P, et al (2023a) RAVEN: in-context learning with retrieval augmented encoder-decoder language models. CoRR abs/2308.07922 — [arXiv:2308.07922](https://arxiv.org/abs/2308.07922) find
  87. Huang Q, Tung AKH (2023) Lightweight-yet-efficient: Revitalizing ball-tree for point-to-hyperplane nearest neighbor search. In: Proceedings of the 39th IEEE International Conference on Data Engineering (ICDE), pp 436–449 find
  88. Huang Q, Fu S, Liu X, et al (2023b) Learning retrieval augmentation for personalized dialogue generation. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 2523–2540 find
  89. Huang X, Liu W, Chen X, et al (2024) Understanding the planning of LLM agents: A survey. CoRR abs/2402.02716 find
  90. Huang Y, Huang J (2024) A survey on retrieval-augmented text generation for large language models. CoRR abs/2404.10981 — [arXiv:2404.10981](https://arxiv.org/abs/2404.10981) find
  91. Huang Y, Liu D, Zhong Z, et al (2023c) knn-adapter: Efficient domain adaptation for black-box language models. CoRR abs/2302.10879. https://doi.org/10.48550/ ARXIV.2302.10879 — [arXiv:2302.10879](https://arxiv.org/abs/2302.10879) find
  92. Hui Y, Lu Y, Zhang H (2024) UDA: A benchmark suite for retrieval augmented generation in real-world document analysis. In: Advances in Neural Information Processing Systems 38 (NeurIPS) find
  93. Ishiwatari S, Yao J, Liu S, et al (2017) Chunk-based decoder for neural machine translation. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL), pp 1901–1912 find
  94. Izacard G, Grave E (2021) Leveraging passage retrieval with generative models for open domain question answering. In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL), pp 874–880
  95. Izacard G, Caron M, Hosseini L, et al (2022) Unsupervised dense information retrieval with contrastive learning. IEEE Transactions on Pattern Analysis and Machine Intelligence 2022
  96. Izacard G, Lewis PSH, Lomeli M, et al (2023) Atlas: Few-shot learning with retrieval augmented language models. Journal of Machine Learning Research 24:251:1–251:43
  97. Jégou H, Douze M, Schmid C (2011) Product quantization for nearest neighbor search. IEEE Transactions on Pattern Analysis and Machine Intelligence 33(1):117–128 find
  98. Ji X, Glenn P, Parameswaran AG, et al (2025) TARGET: benchmarking table retrieval for generative tasks. CoRR abs/2505.11545 — [arXiv:2505.11545](https://arxiv.org/abs/2505.11545) find
  99. Ji Z, Lee N, Frieske R, et al (2023a) Survey of hallucination in natural language generation. ACM Computing Surveys 55(12):248:1–248:38
  100. Ji Z, Liu Z, Lee N, et al (2023b) RHO: reducing hallucination in open-domain dialogues with knowledge grounding. In: Findings of the Association for Computational Linguistics: ACL, pp 4504–4522 find
  101. Jiang AQ, Sablayrolles A, Mensch A, et al (2023a) Mistral 7b. CoRR abs/2310.06825 find
  102. Jiang AQ, Sablayrolles A, Roux A, et al (2024a) Mixtral of experts. CoRR abs/2401.04088. https://doi.org/10.48550/ARXIV.2401.04088 ↗
  103. Jiang H, Lu Z, Meng F, et al (2022) Towards robust k-nearest-neighbor machine translation. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 5468–5477 find
  104. Jiang W, Zhang S, Han B, et al (2024b) Piperag: Fast retrieval-augmented generation via algorithm-system co-design. CoRR abs/2403.05676 — [arXiv:2403.05676](https://arxiv.org/abs/2403.05676) find
  105. Jiang W, Subramanian S, Graves C, et al (2025) RAGO: systematic performance optimization for retrieval-augmented generation serving. In: Proceedings of the 52nd Annual International Symposium on Computer Architecture (ISCA), pp 974–989 find
  106. Jiang Z, Xu FF, Gao L, et al (2023b) Active retrieval augmented generation. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 7969–7992
  107. Jiao X, Yin Y, Shang L, et al (2020) Tinybert: Distilling BERT for natural language understanding. In: Findings of the Association for Computational Linguistics: EMNLP, pp 4163–4174
  108. Jin C, Zhang Z, Jiang X, et al (2024a) Ragcache: Efficient knowledge caching for retrieval-augmented generation. CoRR abs/2404.12457 find
  109. Jin J, Wang H, Zhang H, et al (2024b) DVD: dynamic contrastive decoding for knowledge amplification in multi-document question answering. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 4624–4637 find
  110. Jin Q, Kim W, Chen Q, et al (2023) Medcpt: Contrastive pre-trained transformers with large-scale pubmed search logs for zero-shot biomedical information retrieval. Bioinformatics 39(10) find
  111. Johnson J, Douze M, Jégou H (2021) Billion-scale similarity search with gpus. IEEE Transactions on Big Data 7(3):535–547 de Jong M, Zemlyanskiy Y, FitzGerald N, et al (2022) Mention memory: incorporating textual knowledge into transformers through entity mention attention. In: Proceedings of The Te… find
  112. Kaplan J, McCandlish S, Henighan T, et al (2020) Scaling laws for neural language models. CoRR abs/2001.08361
  113. Karpukhin V, Oguz B, Min S, et al (2020) Dense passage retrieval for open-domain question answering. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 6769–6781
  114. Khandelwal U, Levy O, Jurafsky D, et al (2020) Generalization through memorization: Nearest neighbor language models. In: Proceedings of The 8th International Conference on Learning Representations (ICLR) find
  115. Khandelwal U, Fan A, Jurafsky D, et al (2021) Nearest neighbor machine translation. In: Proceedings of the 9th International Conference on Learning Representations (ICLR) find
  116. Kim K, Lee J (2024) RE-RAG: improving open-domain QA performance and interpretability with relevance estimator in retrieval-augmented generation. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 22149–22161, https://doi.org/10.18653/V1/2024. EMNL… ↗
  117. Kim S, Gholami A, Yao Z, et al (2021) I-BERT: integer-only BERT quantization. In: Proceedings of the 38th International Conference on Machine Learning (ICML), pp 5506–5518
  118. King B, Flanigan J (2023) Diverse retrieval-augmented in-context learning for dialogue state tracking. In: Findings of the Association for Computational Linguistics: ACL, pp 5570–5585 find
  119. Kwiatkowski T, Palomaki J, Redfield O, et al (2019) Natural questions: a benchmark for question answering research. Transactions of the Association for Computational Linguistics 7:452–466
  120. Kwon W, Li Z, Zhuang S, et al (2023) Efficient memory management for large language model serving with pagedattention. In: Proceedings of the 29th Symposium on Operating Systems Principles (SOSP), pp 611–626, https://doi.org/10.1145/ 3600006.3613165
  121. LangChain (2023) LangChain. Software, URL https://www.langchain.com/ ↗
  122. LangChain (2026) Langsmith observability. https://docs.langchain.com/langsmith/ observability, accessed: 2026-03-04 ↗
  123. Lazaridou A, Gribovskaya E, Stokowiec W, et al (2022) Internet-augmented language models through few-shot prompting for open-domain question answering. CoRR abs/2203.05115. https://doi.org/10.48550/ARXIV.2203.05115 ↗
  124. Lee K, Han S, Hwang S, et al (2023) When to read documents or QA history: On unified and selective open-domain QA. In: Findings of the Association for Computational Linguistics: ACL, pp 6420–6432 find
  125. Lee S, Shakir A, Koenig D, et al (2024) Open source strikes bread - new fluffy embeddings model. URL https://www.mixedbread.ai/blog/mxbai-embed-large-v1 ↗
  126. Lehman E, Hernandez E, Mahajan D, et al (2023) Do we still need clinical language models? In: Conference on Health, Inference, and Learning (CHIL), pp 578–597 find
  127. Lewis PSH, Perez E, Piktus A, et al (2020) Retrieval-augmented generation for knowledge-intensive NLP tasks. In: Advances in Neural Information Processing Systems 33 (NeurIPS)
  128. Lewis PSH, Oguz B, Xiong W, et al (2022) Boosted dense retriever. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), pp 3102–3117 find
  129. Li H, Su Y, Cai D, et al (2022a) A survey on retrieval-augmented text generation. CoRR abs/2202.01110 — [arXiv:2202.01110](https://arxiv.org/abs/2202.01110) find
  130. Li H, Xu M, Song Y (2023a) Sentence embedding leaks more information than you expect: Generative embedding inversion attack to recover the whole sentence. In: Findings of the Association for Computational Linguistics: ACL, pp 14022–14040 find
  131. Li M, Wang Y, Zhang P, et al (2023b) Deep learning for approximate nearest neighbour search: A survey and future directions. IEEE Transactions on Knowledge and Data Engineering 35(9):8997–9018 find
  132. Li X, Li P, Hu P (2023c) Revisiting source context in nearest neighbor machine translation. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP) find
  133. Li X, Lv K, Yan H, et al (2023d) Unified demonstration retriever for in-context learning. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), pp 4644–4668
  134. Li Y, Yang Y, Quan X, et al (2021) Retrieve & memorize: Dialog policy learning with multi-action memory. In: Findings of the Association for Computational Linguistics (ACL/IJCNLP), pp 447–459 find
  135. Li Y, Wen H, Wang W, et al (2024a) Personal LLM agents: Insights and survey about the capability, efficiency and security. CoRR abs/2401.05459 find
  136. Li Y, Yue X, Liao Z, et al (2024b) Attributionbench: How hard is automatic attribution evaluation? In: Findings of the Association for Computational Linguistics: ACL, pp 14919–14935 find
  137. Li Z, Guo R, Kumar S (2022b) Decoupled context processing for context augmented language modeling. In: Advances in Neural Information Processing Systems 35 (NeurIPS) find
  138. Liang X, Niu S, Li Z, et al (2025) Saferag: Benchmarking security in retrieval-augmented generation of large language model. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL), pp 4609–4631 find
  139. Lin BY, Tan K, Miller C, et al (2022) Unsupervised cross-task generalization via retrieval augmentation. In: Advances in Neural Information Processing Systems 35 (NeurIPS) find
  140. Liu J (2022) LlamaIndex. https://doi.org/10.5281/zenodo.1234, URL https://github. com/jerryjliu/llama index Liu J, Li L, Xiang T, et al (2023a) TCRA-LLM: token compression retrieval augmented large language model for inference cost reduction. In: Findings of the Association for Computational Linguis… ↗
  141. Liu NF, Lin K, Hewitt J, et al (2024) Lost in the middle: How language models use long contexts. Transactions of the Association for Computational Linguistics 12:157–173
  142. Liu S, Wei Y (2015) Fast nearest neighbor searching based on improved vp-tree. Pattern Recognition Letters 60-61:8–15 find
  143. Liu S, Cho H, Freedman M, et al (2023b) RECAP: retrieval-enhanced context-aware prefix encoder for personalized dialogue response generation. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), pp 8404–8419 find
  144. Liu Y, Ott M, Goyal N, et al (2019) Roberta: A robustly optimized BERT pretraining approach. CoRR abs/1907.11692
  145. Liu Y, Iter D, Xu Y, et al (2023c) G-eval: NLG evaluation using gpt-4 with better human alignment. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 2511–2522
  146. LMDB (2014) LMDB. Software, URL https://github.com/LMDB/lmdb ↗
  147. Luo M, Jain S, Gupta A, et al (2023) A study on the efficiency and generalization of light hybrid retrievers. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), pp 1617–1626 find
  148. Lyu X, Grafberger S, Biegel S, et al (2023) Improving retrieval-augmented large language models via data importance learning. CoRR abs/2307.03027. https://doi.org/ 10.48550/ARXIV.2307.03027 find
  149. Malkov YA, Yashunin DA (2020) Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs. IEEE Transactions on Pattern Analysis and Machine Intelligence 42(4):824–836 find
  150. Manakul P, Liusie A, Gales MJF (2023) Selfcheckgpt: Zero-resource black-box hallucination detection for generative large language models. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 9004–9017, https://doi.org/10.18653/V1/2023.EMNLP-MAIN.557 ↗
  151. Mao S, Jiang Y, Chen B, et al (2024) Rafe: Ranking feedback improves query rewriting for RAG. In: Findings of the Association for Computational Linguistics: EMNLP, pp 884–901, https://doi.org/10.18653/V1/2024.FINDINGS-EMNLP.49 ↗
  152. Martinelli I, Ponti MA (2025) Towards secure retrieval-augmented generation: Preventing LLM data leaks with RBAC. In: Proceedings of the 35th Brazilian Conference on Intelligent Systems (BRACIS), Lecture Notes in Computer Science, vol 16182. Springer, pp 500–515 find
  153. Martins PH, Marinho Z, Martins AFT (2022) Chunk-based nearest neighbor machine translation. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 4228–4245 find
  154. Mei K, Li Z, Xu S, et al (2024) AIOS: LLM agent operating system. CoRR abs/2403.16971 — [arXiv:2403.16971](https://arxiv.org/abs/2403.16971) find
  155. Meng K, Bau D, Andonian A, et al (2022a) Locating and editing factual associations in GPT. In: Advances in Neural Information Processing Systems 35 (NeurIPS) find
  156. Meng Y, Li X, Zheng X, et al (2022b) Fast nearest neighbor machine translation. In: Findings of the Association for Computational Linguistics: ACL, pp 555–565 find
  157. Mesnard T, Hardin C, Dadashi R, et al (2024) Gemma: Open models based on gemini research and technology. CoRR abs/2403.08295 find
  158. Microsoft (2024) Retrieval-augmented generation (rag) applications with autogen. https://microsoft.github.io/autogen/0.2/blog/2023/10/18/RetrieveChat/, accessed: 2026-03-04 ↗
  159. Microsoft (2025a) Adding retrieval augmented generation (rag) to semantic kernel agents. https://learn.microsoft.com/en-us/semantic-kernel/frameworks/agent/ agent-rag?pivots=programming-language-csharp, accessed: 2026-03-04 ↗
  160. Microsoft (2025b) Get started with rag using a prompt flow sample. https://learn.microsoft.com/en-us/azure/machine-learning/ how-to-use-retrieval-augmented-generation?view=azureml-api-2, accessed: 2026-03-04 ↗
  161. Microsoft (2025c) Overview of the microsoft 365 copilot retrieval https://learn.microsoft.com/en-us/microsoft-365-copilot/extensibility/api/ ai-services/retrieval/overview, accessed: 2026-03-04 api. ↗
  162. Microsoft (2026a) Agentic retrieval in azure ai search. https://learn.microsoft.com/ en-us/azure/search/agentic-retrieval-overview, accessed: 2026-03-04 ↗
  163. Microsoft (2026b) Retrieval-augmented generation (rag) in azure ai search. https://learn.microsoft.com/en-us/azure/search/retrieval-augmented-generation-overview, accessed: 2026-03-04 ↗
  164. Mihaylov T, Clark P, Khot T, et al (2018) Can a suit of armor conduct electricity? A new dataset for open book question answering. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 2381–2391 find
  165. Min S, Krishna K, Lyu X, et al (2023a) Factscore: Fine-grained atomic evaluation of factual precision in long form text generation. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 12076–12100
  166. Min S, Shi W, Lewis M, et al (2023b) Nonparametric masked language modeling. In: Findings of the Association for Computational Linguistics: ACL, pp 2097–2118 find
  167. Mueller A, Narang K, Mathias L, et al (2023) Meta-training with demonstration retrieval for efficient few-shot learning. In: Findings of the Association for Computational Linguistics: ACL, pp 6049–6064 find
  168. Muhamed A, Ribeiro LFR, Dreyer M, et al (2025) Refusalbench: Generative evaluation of selective refusal in grounded language models. CoRR abs/2510.10390
  169. Muszynska E (2016) Graph- and surface-level sentence chunking. In: Proceedings of the ACL 2016 Student Research Workshop, pp 93–99 find
  170. Narayan S, Cohen SB, Lapata M (2018) Don’t give me the details, just the summary! topic-aware convolutional neural networks for extreme summarization. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 1797–1807
  171. Ni B, Liu Z, Wang L, et al (2025) Towards trustworthy retrieval augmented generation for large language models: A survey. CoRR abs/2502.06872 — [arXiv:2502.06872](https://arxiv.org/abs/2502.06872)
  172. NLTK (2001) NLTK. misc, URL https://www.nltk.org/ ↗
  173. OpenAI (2022) Text-Emb-Ada. URL https://platform.openai.com/docs/guides/ embeddings OpenAI (2023) GPT-4 technical report. CoRR abs/2303.08774 ↗
  174. OpenAI (2026) Evals – openai api reference. https://platform.openai.com/docs/ api-reference/evals, accessed: 2026-03-04 ↗
  175. Packer C, Fang V, Patil SG, et al (2023) Memgpt: Towards llms as operating systems. CoRR abs/2310.08560 find
  176. Paranjape B, Lamm M, Tenney I (2022) Retrieval-guided counterfactual generation for QA. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL), pp 1670–1686 find
  177. Park J, Cho S, Lee J (2025) Stop-rag: Value-based retrieval control for iterative RAG. CoRR abs/2510.14337. https://doi.org/10.48550/ARXIV.2510.14337 — [doi:10.48550/arxiv.2510.14337](https://doi.org/10.48550/arxiv.2510.14337) ↗
  178. Park S, Lee J (2024) Toward robust ralms: Revealing the impact of imperfect retrieval on retrieval-augmented language models. Transactions of the Association for Computational Linguistics 12:1686–1702 find
  179. Peng X, Qin C, Chen Z, et al (2025) UNIDOC-BENCH: A unified benchmark for document-centric multimodal RAG. CoRR abs/2510.03663 — [arXiv:2510.03663](https://arxiv.org/abs/2510.03663) find
  180. Petroni F, Rocktäschel T, Riedel S, et al (2019) Language models as knowledge bases? In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp 2463–2473
  181. Pipitone N, Alami GH (2024) Legalbench-rag: A benchmark for retrieval-augmented generation in the legal domain. CoRR abs/2408.10343 find
  182. Radford A, Narasimhan K, Salimans T, et al (2018) Improving language understanding by generative pre-training. OpenAI blog Radford A, Wu J, Child R, et al (2019) Language models are unsupervised multitask learners. OpenAI blog 1(8):9 find
  183. Rajaraman A, Ullman JD (2011) Data Mining, Cambridge University Press, p 1–17 find
  184. Rajpurkar P, Jia R, Liang P (2018) Know what you don’t know: Unanswerable questions for squad. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL), pp 784–789
  185. Ram O, Bezalel L, Zicher A, et al (2023a) What are you token about? dense retrieval as distributions over the vocabulary. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), pp 2481–2498 find
  186. Ram O, Levine Y, Dalmedigos I, et al (2023b) In-context retrieval-augmented language models. Transactions of the Association for Computational Linguistics 11:1316– 1331. https://doi.org/10.1162/TACL A 00605 ↗
  187. Ram P, Sinha K (2019) Revisiting kd-tree for nearest neighbor search. In: Teredesai A, Kumar V, Li Y, et al (eds) Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD), pp 1378–1388 find
  188. Reid M, Savinov N, Teplyashin D, et al (2024) Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. CoRR abs/2403.05530
  189. Reimers N, Gurevych I (2019) Sentence-bert: Sentence embeddings using siamese bert-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp 3980–3990
  190. Ren Y, Cao Y, Guo P, et al (2023) Retrieve-and-sample: Document-level event argument extraction via hybrid retrieval augmentation. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), pp 293–306 find
  191. Robertson SE, Zaragoza H (2009) The probabilistic relevance framework: BM25 and beyond. Foundations and Trends in Information Retrieval 3(4):333–389 find
  192. Roy N, Ribeiro LFR, Blloshmi R, et al (2024) Learning when to retrieve, what to rewrite, and how to respond in conversational QA. In: Findings of the Association for Computational Linguistics: EMNLP, pp 10604–10625, https://doi.org/10.18653/ find
  193. Ru D, Qiu L, Hu X, et al (2024) Ragchecker: A fine-grained framework for diagnosing retrieval-augmented generation. In: Advances in Neural Information Processing Systems 38 (NeurIPS) find
  194. Saad-Falcon J, Khattab O, Potts C, et al (2024) ARES: an automated evaluation framework for retrieval-augmented generation systems. In: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), pp 338–354 find
  195. Sachan DS, Reddy S, Hamilton WL, et al (2021) End-to-end training of multi-document reader and retriever for open-domain question answering. In: Advances in Neural Information Processing Systems 34 (NeurIPS), pp 25968–25981
  196. Sanh V, Debut L, Chaumond J, et al (2019) Distilbert, a distilled version of BERT: smaller, faster, cheaper and lighter. CoRR abs/1910.01108 find
  197. Schick T, Dwivedi-Yu J, Dessı̀ R, et al (2023) Toolformer: Language models can teach themselves to use tools. In: Advances in Neural Information Processing Systems 36 (NeurIPS)
  198. Sellam T, Das D, Parikh AP (2020) BLEURT: learning robust metrics for text generation. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL). Association for Computational Linguistics, pp 7881–7892
  199. Shao Z, Gong Y, Shen Y, et al (2023) Enhancing retrieval-augmented large language models with iterative retrieval-generation synergy. In: Findings of the Association for Computational Linguistics: EMNLP, pp 9248–9274
  200. Shen M, Umar M, Maeng K, et al (2024) Towards understanding systems trade-offs in retrieval-augmented generation model inference. CoRR abs/2412.11854 — [arXiv:2412.11854](https://arxiv.org/abs/2412.11854) find
  201. Shi W, Min S, Yasunaga M, et al (2024) REPLUG: retrieval-augmented black-box language models. In: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), pp 8371–8384
  202. Shuster K, Poff S, Chen M, et al (2021) Retrieval augmentation reduces hallucination in conversation. In: Findings of the Association for Computational Linguistics: EMNLP, pp 3784–3803
  203. Siino M, Tinnirello I (2024) GPT hallucination detection through prompt engineering. In: Working Notes of the Conference and Labs of the Evaluation Forum (CLEF), pp 712–721 find
  204. Siino M, Tinnirello I, Cascia ML (2024) Is text preprocessing still worth the time? A comparative survey on the influence of popular preprocessing methods on transformers and traditional classifiers. Inf Syst 121:102342 find
  205. Siino M, Tinnirello I, Cascia ML (2025) From foundations to GPT in text classification: A comprehensive survey on current approaches and future trends. Found Trends Inf Retr 19(5):557–711 find
  206. Singhal K, Azizi S, Tu T, et al (2023a) Large language models encode clinical knowledge. Nature 620(7972):172–180
  207. Singhal K, Tu T, Gottweis J, et al (2023b) Towards expert-level medical question answering with large language models. CoRR abs/2305.09617
  208. Siriwardhana S, Weerasekera R, Kaluarachchi T, et al (2023) Improving the domain adaptation of retrieval augmented generation (RAG) models for open domain question answering. Transactions of the Association for Computational Linguistics 11:1–17
  209. Spotify (2017) Annoy. Software, URL https://github.com/spotify/annoy ↗
  210. Spring (2026) Retrieval augmented generation-spring ai. https://docs.spring.io/ spring-ai/reference/api/retrieval-augmented-generation.html, accessed: 2026-03-04 ↗
  211. Su J, Ahmed MHM, Lu Y, et al (2024a) Roformer: Enhanced transformer with rotary position embedding. Neurocomputing 568:127063
  212. Su W, Tang Y, Ai Q, et al (2024b) DRAGIN: dynamic retrieval augmented generation based on the real-time information needs of large language models. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL), pp 12991–13013, https://doi.org/10.18653/V1/2024.ACL-… ↗
  213. Su W, Tang Y, Ai Q, et al (2025a) Parametric retrieval augmented generation. In: Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), pp 1240–1250 find
  214. Su Y, Collier N (2023) Contrastive search is what you need for neural text generation. Transactions on Machine Learning Research 2023 find
  215. Su Z, Mo F, Nie J (2025b) Parametric retrieval-augmented generation using latent routing of lora adapters. CoRR abs/2511.17044 — [arXiv:2511.17044](https://arxiv.org/abs/2511.17044) find
  216. Sulem E, Hay J, Roth D (2021) Do we know what we don’t know? studying unanswerable questions beyond squad 2.0. In: Findings of the Association for Computational Linguistics: EMNLP, pp 4543–4548 find
  217. Sun J, Xu C, Tang L, et al (2024) Think-on-graph: Deep and responsible reasoning of large language model on knowledge graph. In: Proceedings of The Twelfth International Conference on Learning Representations (ICLR) find
  218. Tan Y, He S, Liao H, et al (2025) Dynamic parametric retrieval augmented generation for test-time knowledge enhancement. CoRR abs/2503.23895 — [arXiv:2503.23895](https://arxiv.org/abs/2503.23895) find
  219. Team L (2024) The llama 3 herd of models. CoRR abs/2407.21783
  220. Thakur N, Reimers N, Rücklé A, et al (2021) BEIR: A heterogeneous benchmark for zero-shot evaluation of information retrieval models. In: Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS Datasets and Benchmarks) find
  221. Touvron H, Lavril T, Izacard G, et al (2023a) Llama: Open and efficient foundation language models. CoRR abs/2302.13971
  222. Touvron H, Martin L, Stone K, et al (2023b) Llama 2: Open foundation and fine-tuned chat models. CoRR abs/2307.09288
  223. Uddin MN, Saeidi A, Handa D, et al (2025) Unseentimeqa: Time-sensitive question-answering beyond llms’ memorization. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL), pp 1873–1913
  224. Vaithilingam P, Zhang T, Glassman EL (2022) Expectation vs. experience: Evaluating the usability of code generation tools powered by large language models. In: Barbosa SDJ, Lampe C, Appert C, et al (eds) CHI Conference on Human Factors in Computing Systems (CHI), pp 332:1–332:7 find
  225. Vaswani A, Shazeer N, Parmar N, et al (2017) Attention is all you need. In: Advances in Neural Information Processing Systems 30 (NeurIPS), pp 5998–6008
  226. Vercel (2026) Rag agent guide – vercel ai sdk. https://ai-sdk.dev/cookbook/guides/ rag-chatbot, accessed: 2026-03-04 ↗
  227. Vu T, Iyyer M, Wang X, et al (2024) Freshllms: Refreshing large language models with search engine augmentation. In: Findings of the Association for Computational Linguistics: ACL, pp 13697–13720, https://doi.org/10.18653/V1/2024. FINDINGS-ACL.813 ↗
  228. Wang B, Ping W, Xu P, et al (2023a) Shall we pretrain autoregressive language models with retrieval? A comprehensive study. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 7763–7786 find
  229. Wang B, Ping W, McAfee L, et al (2024a) Instructretro: Instruction tuning post retrieval-augmented pretraining. In: Proceedings of the Forty-first International Conference on Machine Learning (ICML), pp 51255–51272 find
  230. Wang J, Yi X, Guo R, et al (2021a) Milvus: A purpose-built vector data management system. In: SIGMOD ’21: International Conference on Management of Data. ACM, pp 2614–2627 find
  231. Wang L, Ma C, Feng X, et al (2024b) A survey on large language model based autonomous agents. Frontiers in Computer Science 18(6):186345
  232. Wang S, Xu Y, Fang Y, et al (2022) Training data is more valuable than you think: A simple and effective method by retrieving from training data. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL), pp 3170–3179 find
  233. Wang S, Zhu Y, Liu H, et al (2025a) Knowledge editing for large language models: A survey. ACM Computing Surveys 57(3):59:1–59:37
  234. Wang W, Dong L, Cheng H, et al (2023b) Augmenting language models with long-term memory. In: Advances in Neural Information Processing Systems 36 (NeurIPS) find
  235. Wang W, Zou W, Min J (2025b) Solving LLM repetition problem in production: A comprehensive study of multiple solutions. CoRR abs/2512.04419. https://doi.org/ 10.48550/ARXIV.2512.04419 — [doi:10.48550/arxiv.2512.04419](https://doi.org/10.48550/arxiv.2512.04419) find
  236. Wang X, Jiang Y, Bach N, et al (2021b) Improving named entity recognition by external context retrieving and cooperative learning. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (A…
  237. Wang Y, Li P, Sun M, et al (2023c) Self-knowledge guided retrieval augmentation for large language models. In: Findings of the Association for Computational Linguistics: EMNLP, pp 10303–10315
  238. Wang Z, Araki J, Jiang Z, et al (2023d) Learning to filter context for retrieval-augmented generation. CoRR abs/2311.08377. https://doi.org/10.48550/ARXIV. 2311.08377 ↗
  239. Wang Z, Nie W, Qiao Z, et al (2023e) Retrieval-based controllable molecule generation. In: The Eleventh International Conference on Learning Representations, (ICLR) find
  240. Wornow M, Lozano A, Dash D, et al (2024) Zero-shot clinical trial patient matching with llms. CoRR abs/2402.05125 — [arXiv:2402.05125](https://arxiv.org/abs/2402.05125) find
  241. Wu M, Goodman ND (2018) Multimodal generative models for scalable weakly-supervised learning. In: Advances in Neural Information Processing Systems 31 (NeurIPS), pp 5580–5590 find
  242. Wu S, Xiong Y, Cui Y, et al (2024) Refusion: Improving natural language understanding with computation-efficient retrieval representation fusion. In: Proceedings of The Twelfth International Conference on Learning Representations (ICLR) find
  243. Wu Y, Rabe MN, Hutchins D, et al (2022) Memorizing transformers. In: Proceedings of The Tenth International Conference on Learning Representations (ICLR) find
  244. Xi Z, Chen W, Guo X, et al (2025) The rise and potential of large language model based agents: a survey. Science China Information Sciences 68(2)
  245. Xia S, Wang X, Liang J, et al (2025) Ground every sentence: Improving retrieval-augmented llms with interleaved reference-claim generation. In: Findings of the Association for Computational Linguistics (NAACL), pp 969–988 find
  246. Xiang Z, Wu C, Zhang Q, et al (2025) When to use graphs in RAG: A comprehensive analysis for graph retrieval-augmented generation. CoRR abs/2506.05690 — [arXiv:2506.05690](https://arxiv.org/abs/2506.05690) find
  247. Xiao S, Liu Z, Zhang P, et al (2023) C-pack: Packaged resources to advance general chinese embedding. CoRR abs/2309.07597
  248. Xie J, Chen Z, Zhang R, et al (2024) Large multimodal agents: A survey. CoRR abs/2402.15116 — [arXiv:2402.15116](https://arxiv.org/abs/2402.15116) find
  249. Xin J, Tang R, Yu Y, et al (2021) The art of abstention: Selective prediction and error regularization for natural language processing. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processi… find
  250. Xiong G, Jin Q, Lu Z, et al (2024) Benchmarking retrieval-augmented generation for medicine. In: Findings of the Association for Computational Linguistics: ACL, pp 6233–6251
  251. Xiong Y, Yang X, Liu L, et al (2023) EARA: improving biomedical semantic textual similarity with entity-aligned attention and retrieval augmentation. In: Findings of the Association for Computational Linguistics: EMNLP, pp 8760–8771 find
  252. Xu F, Shi W, Choi E (2024) RECOMP: improving retrieval-augmented lms with context compression and selective augmentation. In: Proceedings of The Twelfth International Conference on Learning Representations (ICLR) find
  253. Xu FF, Alon U, Neubig G (2023) Why do nearest neighbor language models work? In: Proceedings of the 40th International Conference on Machine Learning (ICML), pp 38325–38341 find
  254. Yan S, Gu J, Zhu Y, et al (2024) Corrective retrieval augmented generation. CoRR abs/2401.15884
  255. Yang A, Yang B, Hui B, et al (2024a) Qwen2 technical report. CoRR abs/2407.10671 find
  256. Yang A, Yang B, Zhang B, et al (2024b) Qwen2.5 technical report. CoRR abs/2412.15115 find
  257. Yang Z, Qi P, Zhang S, et al (2018) Hotpotqa: A dataset for diverse, explainable multi-hop question answering. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 2369–2380
  258. Yu G, Liu L, Jiang H, et al (2023a) Retrieval-augmented few-shot text classification. In: Findings of the Association for Computational Linguistics: EMNLP, pp 6721–6735 find
  259. Yu H, Gan A, Zhang K, et al (2024) Evaluation of retrieval-augmented generation: A survey. CoRR abs/2405.07437 — [arXiv:2405.07437](https://arxiv.org/abs/2405.07437) find
  260. Yu X, Jian P, Chen C (2025) Tablerag: A retrieval augmented generation framework for heterogeneous document reasoning. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 14063–14082 find
  261. Yu Z, Xiong C, Yu S, et al (2023b) Augmentation-adapted retriever improves generalization of language models as generic plug-in. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), pp 2421–2436 find
  262. Yue X, Wang B, Chen Z, et al (2023) Automatic evaluation of attribution by large language models. In: Findings of the Association for Computational Linguistics: EMNLP, pp 4615–4635 find
  263. Zeng A, Liu X, Du Z, et al (2023) GLM-130B: an open bilingual pre-trained model. In: The Eleventh International Conference on Learning Representations (ICLR).
  264. OpenReview.net Zeng S, Zhang J, He P, et al (2025) Mitigating the privacy issues in retrieval-augmented generation (RAG) via pure synthetic data. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 24527–24558 find
  265. Zhang B, Sennrich R (2019) Root mean square layer normalization. In: Advances in Neural Information Processing Systems 32 (NeurIPS), pp 12360–12371 find
  266. Zhang H, Chen J, Jiang F, et al (2023a) Huatuogpt, towards taming language model to be a doctor. In: Findings of the Association for Computational Linguistics: EMNLP, pp 10859–10885
  267. Zhang J, Muhamed A, Anantharaman A, et al (2023b) Reaugkd: Retrieval-augmented knowledge distillation for pre-trained language models. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), pp 1128– 1136 find
  268. Zhang N, Yao Y, Tian B, et al (2024) A comprehensive study of knowledge editing for large language models. CoRR abs/2401.01286 find
  269. Zhang Z, Dai Q, Bo X, et al (2025) A survey on the memory mechanism of large language model-based agents. ACM Transactions on Information Systems 43(6):155:1–155:47 find
  270. Zhao P, Zhang H, Yu Q, et al (2024) Retrieval-augmented generation for ai-generated content: A survey. CoRR abs/2402.19473
  271. Zheng L, Chiang W, Sheng Y, et al (2023) Judging llm-as-a-judge with mt-bench and chatbot arena. In: Advances in Neural Information Processing Systems 36 (NeurIPS)
  272. Zheng X, Zhang Z, Guo J, et al (2021) Adaptive nearest neighbor machine translation. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL/IJCNLP), pp 368–374, https://doi.org/10.186…
  273. Zhong Z, Lei T, Chen D (2022) Training language models with memory augmentation. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 5657–5673, https://doi.org/10.18653/V1/2022. EMNLP-MAIN.382 ↗
  274. Zhu R, Liu X, Sun Z, et al (2025) Mitigating lost-in-retrieval problems in retrieval augmented multi-hop question answering. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL), pp 22362–22375
  275. Zhu W, Xu J, Huang S, et al (2023) INK: injecting knn knowledge in nearest neighbor machine translation. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), pp 15948–15959 find
  276. Zou W, Geng R, Wang B, et al (2025) Poisonedrag: Knowledge corruption attacks to retrieval-augmented generation of large language models. In: Proceedings of the 34th USENIX Security Symposium (USENIX Security), pp 3827–3844 find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wu-2024-retrieval-augmented-generation-natural-language/