mlsanityData to 7 Oct 2026

Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation

arXiv 2402.18150 ↗First posted 28 Feb 2024cs.CL cs.AI cs.IRcited by 19

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating additional information from retrieval. However, studies have shown that LLMs still face challenges in effectively using the retrieved information, even ignoring it or being misled by it. The key reason is that the training of LLMs does not clearly make LLMs learn how to utilize input retrieved texts with varied quality. In this paper, we propose a novel perspective that considers the role of LLMs in RAG as ``Information Refiner'', which means that regardless of correctness, completeness, or usefulness of retrieved texts, LLMs can consistently integrate knowledge within the retrieved texts and model parameters to generate the texts that are more concise, accurate, and complete than the retrieved texts. To this end, we propose an information refinement training method named InFO-RAG that optimizes LLMs for RAG in an unsupervised manner. InFO-RAG is low-cost and general across various tasks. Extensive experiments on zero-shot prediction of 11 datasets in diverse tasks including Question Answering, Slot-Filling, Language Modeling, Dialogue, and Code Generation show that InFO-RAG improves the performance of LLaMA2 by an average of 9.39% relative points. InFO-RAG also shows advantages in in-context learning and robustness of RAG.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 36 of its 56 references that are in the map. First posted on arXiv 28 Feb 2024.

Builds on

36 of 56 references.

References · 36

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  6. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  7. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  8. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  9. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  10. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  11. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  12. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
24 more
  1. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  2. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  3. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  4. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  5. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  6. 2019CodeSearchNet Challenge: Evaluating the State of Semantic Code Searchcited by 638
  7. 2023An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuningcited by 622
  8. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 571
  9. 2019ELI5: Long Form Question Answeringcited by 567
  10. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  11. 2020CodeBLEU: a Method for Automatic Evaluation of Code Synthesiscited by 468
  12. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 464
  13. 2017Zero-Shot Relation Extraction via Reading Comprehensioncited by 425
  14. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
  15. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 351
  16. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 316
  17. 2023Benchmarking Large Language Models in Retrieval-Augmented Generationcited by 307
  18. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 180
  19. 2021Retrieval Augmented Code Generation and Summarizationcited by 148
  20. 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 146
  21. 2018Mapping Language to Code in Programmatic Contextcited by 104
  22. 2018Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memorycited by 49
  23. 2023RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modelingcited by 12
  24. 2024List-aware Reranking-Truncation Joint Model for Search and Retrieval-augmented Generationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 9; 2026: 4.

19 papers.

Sort:

By area:

  1. 2025Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learningcited by 39
  2. 2024RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewardscited by 33
  3. 2024OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generationcited by 24
  4. 2024Cross-Modal Safety Mechanism Transfer in Large Vision-Language Modelscited by 18
  5. 2024MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Modelscited by 11
  6. 2025Iterative Self-Incentivization Empowers Large Language Models as Agentic Searcherscited by 11
  7. 2025Resisting Contextual Interference in RAG via Parametric-Knowledge Reinforcementcited by 11
  8. 2025RLKD: Distilling LLMs' Reasoning via Reinforcement Learningcited by 10
  9. 2024A Theory for Token-Level Harmonization in Retrieval-Augmented Generationcited by 7
  10. 2025Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignmentcited by 7
  11. 2025RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-Thoughtscited by 6
  12. 2026SF-RAG: Structure-Fidelity Retrieval-Augmented Generation for Academic Question Answeringcited by 2
7 more
  1. 2026Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directionscited by 2
  2. 2024QCG-Rerank: Chunks Graph Rerank with Query Expansion in Retrieval-Augmented LLMs for Tourism Domaincited by 1
  3. 2025Magic Mushroom: A Customizable Benchmark for Fine-grained Analysis of Retrieval Noise Erosion in RAG Systemscited by 1
  4. 2025TAdaRAG: Task Adaptive Retrieval-Augmented Generation via On-the-Fly Knowledge Graph Constructioncited by 1
  5. 2026MC-RAG System: A Structure-Driven RAG System for Multi-Constraint Queriescited by 1
  6. 2025CKD-EHR:Clinical Knowledge Distillation for Electronic Health Recordscited by 0
  7. 2026Disentangling Deception and Hallucination Failures in LLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024A Survey on Retrieval-Augmented Text Generation for Large Language Models
  2. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
  3. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models
  4. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation
  5. 2025Post-training an LLM for RAG? Train on Self-Generated Demonstrations
  6. 2025When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs
  7. 2024Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models
  8. 2024Retrieval-Augmented Machine Translation with Unstructured Knowledge