mlsanityData to 14 Oct 2026

The Distracting Effect: Understanding Irrelevant Passages in RAG

arXiv 2505.06914 ↗First posted 11 May 2025cs.CL cs.IRcited by 33

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

Abstract (arXiv)

A well-known issue with Retrieval Augmented Generation (RAG) is that retrieved passages that are irrelevant to the query sometimes distract the answer-generating LLM, causing it to provide an incorrect response. In this paper, we shed light on this core issue and formulate the distracting effect of a passage w.r.t. a query (and an LLM). We provide a quantifiable measure of the distracting effect of a passage and demonstrate its robustness across LLMs. Our research introduces novel methods for identifying and using hard distracting passages to improve RAG systems. By fine-tuning LLMs with these carefully selected distracting passages, we achieve up to a 7.5% increase in answering accuracy compared to counterparts fine-tuned on conventional RAG datasets. Our contribution is two-fold: first, we move beyond the simple binary classification of irrelevant passages as either completely unrelated vs. distracting, and second, we develop and analyze multiple methods for finding hard distracting passages. To our knowledge, no other research has provided such a comprehensive framework for identifying and utilizing hard distracting passages.

Key facts. Cited by 33 papers in the map (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 19 of its 29 references that are in the map. First posted on arXiv 11 May 2025.

Builds on

19 of 29 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales19 Jun
  2. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 17

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  3. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  4. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  5. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  6. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 849
  7. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  8. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 573
  9. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 369
  10. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 281
  11. 2023RA-DIT: Retrieval-Augmented Dual Instruction Tuningcited by 195
  12. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 184
5 more
  1. 2022Large Language Models with Controllable Working Memorycited by 169
  2. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAGcited by 123
  3. 2024NV-Retriever: Improving text embedding models with effective hard-negative miningcited by 84
  4. 2024Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Modelscited by 40
  5. 2024LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statementscited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 25.

33 papers.

Sort:

By area:

  1. 2025Do RAG Systems Really Suffer From Positional Bias?cited by 12
  2. 2026What Papers Don't Tell You: Recovering Tacit Knowledge for Automated Paper Reproductioncited by 6
  3. 2025Prompting Large Language Models with Partial Knowledge for Answering Questions with Unseen Entitiescited by 4
  4. 2025Redefining Retrieval Evaluation in the Era of LLMscited by 3
  5. 2025Dynamic Context Selection for Retrieval-Augmented Generation: Mitigating Distractors and Positional Biascited by 3
  6. 2026Beyond Code Snippets: Benchmarking LLMs on Repository-Level Question Answeringcited by 3
  7. 2026Memory Retrieval for Changing Preferencescited by 3
  8. 2026Large Language Models Lack Temporal Awareness of Medical Knowledgecited by 2
  9. 2025MeVe: A Modular System for Memory Verification and Effective Context Control in Language Modelscited by 1
  10. 2025Relevance to Utility: Process-Supervised Rewrite for RAGcited by 1
  11. 2025How important is Recall for Measuring Retrieval Quality?cited by 1
  12. 2026Predicting the Benefit of Retrieval Augmentation in Open-Domain Question Answeringcited by 1
21 more
  1. 2026Purifying Multimodal Retrieval: Fragment-Level Evidence Selection for RAGcited by 1
  2. 2026LLM-Oriented Information Retrieval: A Denoising-First Perspectivecited by 1
  3. 2026Lost in the Evidence? Reproducing Document Position and Context Size Effects in RAGcited by 1
  4. 2026On the impact of retrieved content representations in RAG Pipelinescited by 1
  5. 2026The Powerless Noise: How Experimental Settings Shape the Reported Power of Noisecited by 1
  6. 2026Predicting Partial Answer Quality and Utility in Agentic Retrieval-Augmented Generationcited by 1
  7. 2025Beyond RAG vs. Long-Context: Learning Distraction-Aware Retrieval for Efficient Knowledge Groundingcited by 0
  8. 2026ReFilter: Improving Robustness of Retrieval-Augmented Generation via Gated Filtercited by 0
  9. 2026Mitigating LLM Hallucinations through Domain-Grounded Tiered Retrievalcited by 0
  10. 2026Hypothesis-Conditioned Query Rewriting for Decision-Useful Retrievalcited by 0
  11. 2026Context Selection for Hypothesis and Statistical Evidence Extraction from Full-Text Scientific Articlescited by 0
  12. 2026Natural Language Query to Configuration for Retrieval Agentscited by 0
  13. 2026Memory Makes the Difference: Evaluating How Different Memory Roles Shape Conversational Agentscited by 0
  14. 2026Polistemics: Evaluating LLMs as Information Mediators in Politics & Electionscited by 0
  15. 2026GuidedRAG: Semantic Steering of Retrieval-Augmented Generationcited by 0
  16. 2026When Irrelevant Text Matters: Affine Margin Shifts in Multimodal Large Language Modelscited by 0
  17. 2026Research Design Tracking and Assessment for the Social Sciencescited by 0
  18. 2026Faithfulness Is Not Free: Auditing Offline KV-Cache Quantization in Retrieval-Augmented Generationcited by 0
  19. 2026Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrievalcited by 0
  20. 2026ROAM: Robust Organization of Atomic Memories for Agents through Semantic Relationscited by 0
  21. 2026MemeLogos: Knowledge-Driven Retrieval-Augmented Reasoning for Harmful Meme Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Separating Semantic Competition from Context Length in RAG Reading
  2. 2024In Defense of RAG in the Era of Long-Context Language Models
  3. 2026A Systems-Level Analysis of Sensitivity, Robustness, and Stability in Retrieval-Augmented Generation
  4. 2025Enhancing Retrieval-Augmented Generation: A Study of Best Practices
  5. 2026Know Before You Fetch: Calibrated Retrieval-Budget Allocation for Retrieval-Augmented Generation
  6. 2026Tackling the Inherent Difficulty of Noise Filtering in RAG
  7. 2024Introducing a new hyper-parameter for RAG: Context Window Utilization
  8. 2024Better RAG using Relevant Information Gain