mlsanityData to 7 Oct 2026

Finetune-RAG: Fine-Tuning Language Models to Resist Hallucination in Retrieval-Augmented Generation

arXiv 2505.10792 ↗First posted 16 May 2025cs.CLcited by 2

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) has emerged as a powerful framework to improve factuality in large language models (LLMs) by grounding their outputs in retrieved documents. However, ensuring perfect retrieval of relevant information remains challenging, and when irrelevant content is passed downstream to an LLM, it can lead to hallucinations. In this work, we propose Finetune-RAG, a simple and effective fine-tuning approach that features the first-of-its-kind RAG training dataset constructed to mimic real-world imperfections. Experimental results show that Finetune-RAG improves factual accuracy by 21.2% over the base model. We also propose Bench-RAG, an LLM-as-a-judge evaluation pipeline that stress tests models under realistic imperfect retrieval scenarios. Our codebase and dataset are fully open sourced for community use.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 28 of its 32 references that are in the map. First posted on arXiv 16 May 2025.

Builds on

28 of 32 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Trustworthiness in Retrieval-Augmented Generation Systems: A Survey16 Sep

Other references · 27

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  4. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  5. 2024A Survey on LLM-as-a-Judgecited by 1,384
  6. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  7. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  8. 2024From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judgecited by 480
  9. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 386
  10. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
  11. 2023CodeT5+: Open Code Large Language Models for Code Understanding and Generationcited by 327
  12. 2024Large Legal Fictions: Profiling Legal Hallucinations in Large Language Modelscited by 144
15 more
  1. 2024Seven Failure Points When Engineering a Retrieval Augmented Generation Systemcited by 138
  2. 2023The Troubling Emergence of Hallucination in Large Language Models -- An Extensive Definition, Quantification, and Prescriptive Remediationscited by 130
  3. 2023R-Tuning: Instructing Large Language Models to Say `I Don't Know'cited by 106
  4. 2024Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrieverscited by 83
  5. 2023On Learning to Summarize with Large Language Models as Referencescited by 80
  6. 2024StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurizationcited by 70
  7. 2024Do LLMs Know about Hallucination? An Empirical Investigation of LLM's Hidden Statescited by 50
  8. 2024Don't Forget to Connect! Improving RAG with Graph-based Rerankingcited by 49
  9. 2023Deficiency of Large Language Models in Finance: An Empirical Examination of Hallucinationcited by 41
  10. 2025Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Studycited by 38
  11. 2023Teaching Language Models to Hallucinate Less with Synthetic Taskscited by 31
  12. 2024MedHalu: Hallucinations in Responses to Healthcare Queries by Large Language Modelscited by 20
  13. 2025SRAG: Structured Retrieval-Augmented Generation for Multi-Entity Question Answering over Wikipedia Graphcited by 10
  14. 2023A Step Closer to Comprehensive Answers: Constrained Multi-Stage Question Decomposition with Large Language Modelscited by 4
  15. 2025OpenRAG: Optimizing RAG End-to-End via In-Context Retrieval Learningcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026RAGAL: A Frugal, Fully Local Retrieval-Augmented Assistant for Technical Support at a Government Agencycited by 0
  2. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation
  2. 2025RAG-Check: Evaluating Multimodal Retrieval Augmented Generation Performance
  3. 2024Pandora's Box or Aladdin's Lamp: A Comprehensive Analysis Revealing the Role of RAG Noise in Large Language Models
  4. 2024Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases
  5. 2026Tackling the Inherent Difficulty of Noise Filtering in RAG
  6. 2024Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models
  7. 2025ConfRAG: Confidence-Guided Retrieval-Augmenting Generation
  8. 2025Towards Lighter and Robust Evaluation for Retrieval Augmented Generation