mlsanityData to 7 Oct 2026

RbFT: Robust Fine-tuning for Retrieval-Augmented Generation against Retrieval Defects

arXiv 2501.18365 ↗First posted 30 Jan 2025cs.CL cs.IRcited by 27

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

Abstract (arXiv)

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieved from a knowledge base. However, its effectiveness is fundamentally constrained by the reliability of both the retriever and the knowledge base. In real-world scenarios, imperfections in these components often lead to the retrieval of noisy, irrelevant, or misleading counterfactual information, ultimately undermining the trustworthiness of RAG systems. To address this challenge, we propose Robust Fine-Tuning (RbFT), a method designed to enhance the resilience of LLMs against retrieval defects through two targeted fine-tuning tasks. Experimental results demonstrate that RbFT significantly improves the robustness of RAG systems across diverse retrieval conditions, surpassing existing methods while maintaining high inference efficiency and compatibility with other robustness techniques.

Key facts. Cited by 27 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 38 of its 53 references that are in the map. First posted on arXiv 30 Jan 2025.

Builds on

38 of 53 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Trustworthiness in Retrieval-Augmented Generation Systems: A Survey16 Sep
  2. 2024InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales19 Jun
  3. 2023Benchmarking Large Language Models in Retrieval-Augmented Generation4 Sep

Other references · 35

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  5. 2024Qwen2.5 Technical Reportcited by 4,713
  6. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  7. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  8. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  9. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  10. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  11. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
  12. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
23 more
  1. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  2. 2020RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answeringcited by 410
  3. 2024Graph Retrieval-Augmented Generation: A Surveycited by 320
  4. 2022Promptagator: Few-shot Dense Retrieval From 8 Examplescited by 233
  5. 2022MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Textcited by 216
  6. 2022A Survey on Retrieval-Augmented Text Generationcited by 157
  7. 2021Optimizing Dense Retrieval Model Training with Hard Negativescited by 154
  8. 2024Certifiably Robust RAG against Retrieval Corruptioncited by 144
  9. 2023On the Risk of Misinformation Pollution with Large Language Modelscited by 124
  10. 2023GPTEval: A Survey on Assessments of ChatGPT and GPT-4cited by 73
  11. 2024Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbationscited by 64
  12. 2024Scaling Retrieval-Based Language Models with a Trillion-Token Datastorecited by 54
  13. 2022Synthetic Disinformation Attacks on Automated Fact Verification Systemscited by 44
  14. 2021Attacking Open-domain Question Answering by Injecting Misinformationcited by 41
  15. 2023LeanContext: Cost-Efficient Domain-Specific Question Answering Using LLMscited by 40
  16. 2023Retrieving Supporting Evidence for Generative Question Answeringcited by 31
  17. 2024Knowledge Editing through Chain-of-Thoughtcited by 26
  18. 2024Towards a Search Engine for Machines: Unified Ranking for Multiple Retrieval-Augmented Large Language Modelscited by 23
  19. 2024Mitigating Entity-Level Hallucination in Large Language Modelscited by 17
  20. 2023Wikiformer: Pre-training with Structured Information of Wikipedia for Ad-hoc Retrievalcited by 15
  21. 2023THUIR2 at NTCIR-16 Session Search (SS) Taskcited by 12
  22. 2024LeKUBE: A Legal Knowledge Update BEnchmarkcited by 12
  23. 2022TegTok: Augmenting Text Generation via Task-specific and Open-world Knowledgecited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 11; 2026: 16.

27 papers.

Sort:

By area:

  1. 2025LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directionscited by 49
  2. 2026Skill Retrieval Augmentation for Agentic AIcited by 41
  3. 2025Topic-FlipRAG: Topic-Orientated Adversarial Opinion Manipulation Attacks to Retrieval-Augmented Generation Modelscited by 32
  4. 2025JuDGE: Benchmarking Judgment Document Generation for Chinese Legal Systemcited by 18
  5. 2025SurGE: A Benchmark and Evaluation Framework for Scientific Survey Generationcited by 14
  6. 2025Joint Evaluation of Answer and Reasoning Consistency for Hallucination Detection in Large Reasoning Modelscited by 13
  7. 2025Augmenting Multi-Agent Communication with State Delta Trajectorycited by 13
  8. 2025Decoupling Reasoning and Knowledge Injection for In-Context Knowledge Editingcited by 12
  9. 2026OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality in RAGcited by 11
  10. 2025Out of Style: RAG's Fragility to Linguistic Variationcited by 10
  11. 2025Curriculum Guided Reinforcement Learning for Efficient Multi Hop Retrieval Augmented Generationcited by 5
  12. 2026Enhancing Judgment Document Generation via Agentic Legal Information Collection and Rubric-Guided Optimizationcited by 5
15 more
  1. 2025Confident RAG: Enhancing the Performance of LLMs for Mathematics Question Answering through Multi-Embedding and Confidence Scoringcited by 2
  2. 2026Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directionscited by 2
  3. 2025Magic Mushroom: A Customizable Benchmark for Fine-grained Analysis of Retrieval Noise Erosion in RAG Systemscited by 1
  4. 2026Improve Large Language Model Systems with User Logscited by 1
  5. 2026LLM-Oriented Information Retrieval: A Denoising-First Perspectivecited by 1
  6. 2026When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapsecited by 1
  7. 2026Rethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Rankingcited by 0
  8. 2026LitSeg: Narrative-Aware Document Segmentation for Literary RAGcited by 0
  9. 2026Decoupled Mixture-of-Experts for Parametric Knowledge Injectioncited by 0
  10. 2026Retrievable Gradients: Continual Post-Training Without Cumulative Weight Driftcited by 0
  11. 2026MetaSyn: A Benchmark for LLM Agents on Meta-Analysis Articles from Nature Portfoliocited by 0
  12. 2026RWGBench: Evaluating Scholarly Positioning in Related Work Generationcited by 0
  13. 2026Certified Domain Consistency for Multi-Domain Retrieval: Label-Free Per-Domain Contamination Control with Conformal Risk Guaranteescited by 0
  14. 2026TriShieldRAG: 3 Rings, One Blind Spot in Layered Defenses for Retrieval-Augmented Generationcited by 0
  15. 2026Retrieved But Not Reliable: A Survey on Attacks, and Defenses in Retrieval-Augmented Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Evaluating the Retrieval Robustness of Large Language Models
  2. 2024Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models
  3. 2026Towards Robust Retrieval-Augmented Generation Based on Knowledge Graph: A Comparative Analysis
  4. 2024Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledge
  5. 2025Investigating the Robustness of Retrieval-Augmented Generation at the Query Level
  6. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
  7. 2024RAGGED: Towards Informed Design of Scalable and Stable RAG Systems
  8. 2025Finetune-RAG: Fine-Tuning Language Models to Resist Hallucination in Retrieval-Augmented Generation