mlsanityData to 14 Oct 2026

LLM-Oriented Information Retrieval: A Denoising-First Perspective

arXiv 2605.00505 ↗First posted 1 May 2026cs.IR cs.AI cs.CLcited by 1

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

also in 1 more
Abstract (arXiv)

Modern information retrieval (IR) is no longer consumed primarily by humans but increasingly by large language models (LLMs) via retrieval-augmented generation (RAG) and agentic search. Unlike human users, LLMs are constrained by limited attention budgets and are uniquely vulnerable to noise; misleading or irrelevant information is no longer just a nuisance, but a direct cause of hallucinations and reasoning failures. In this perspective paper, we argue that denoising-maximizing usable evidence density and verifiability within a context window-is becoming the primary bottleneck across the full information access pipeline. We conceptualize this paradigm shift through a four-stage framework of IR challenges: from inaccessible to undiscoverable, to misaligned, and finally to unverifiable. Furthermore, we provide a pipeline-organized taxonomy of signal-to-noise optimization techniques, spanning indexing, retrieval, context engineering, verification, and agentic workflow. We also present research works on information denoising in domains that rely heavily on retrieval such as lifelong assistant, coding agent, deep research, and multimodal understanding.

Key facts. Cited by 1 paper 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 164 of its 221 references that are in the map. First posted on arXiv 1 May 2026.

Builds on

164 of 221 references.

Closest ancestors · 14

Same direction, newest first

  1. 2025The Distracting Effect: Understanding Irrelevant Passages in RAG11 May
  2. 2025Retrieval-Augmented Generation with Conflicting Evidence17 Apr
  3. 2025SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction3 Mar
  4. 2025RbFT: Robust Fine-tuning for Retrieval-Augmented Generation against Retrieval Defects30 Jan
  5. 2024Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models9 Oct
  6. 2024FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"30 Sep
  7. 2024In Defense of RAG in the Era of Long-Context Language Models3 Sep
  8. 2024WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia19 Jun
  9. 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents16 Apr
  10. 2024Spiral of Silence: How is Large Language Model Killing Information Retrieval? -- A Case Study on Open Domain Question Answering16 Apr
  11. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation31 Mar
  12. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity21 Mar
2 more
  1. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct
  2. 2023Benchmarking Large Language Models in Retrieval-Augmented Generation4 Sep

Other references · 150

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  5. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  6. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  7. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
  8. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  9. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
  10. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,443
  11. 2023LongBench: A Bilingual, Multitask Benchmark for Long Context Understandingcited by 1,417
  12. 2024Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysiscited by 1,413
38 more
  1. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  2. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  3. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  4. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  5. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,178
  6. 2024The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scalecited by 1,160
  7. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  8. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  9. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  10. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  11. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 849
  12. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  13. 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 830
  14. 2023DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvaturecited by 726
  15. 2021Deduplicating Training Data Makes Language Models Bettercited by 714
  16. 2019Passage Re-ranking with BERTcited by 645
  17. 2017Towards Automatic Learning of Procedures from Web Instructional Videoscited by 619
  18. 2023Prompt Injection attack against LLM-integrated Applicationscited by 605
  19. 2023Enabling Large Language Models to Generate Text with Citationscited by 595
  20. 2026Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfacescited by 585
  21. 2017TALL: Temporal Activity Localization via Language Querycited by 584
  22. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 556
  23. 2019CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Datacited by 548
  24. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 532
  25. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  26. 2023Active Retrieval Augmented Generationcited by 516
  27. 2019GLTR: Statistical Detection and Visualization of Generated Textcited by 496
  28. 2024Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Researchcited by 483
  29. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 476
  30. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 453
  31. 2024AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Basescited by 429
  32. 2020RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answeringcited by 413
  33. 2024DataComp-LM: In search of the next generation of training sets for language modelscited by 398
  34. 2023Learning to Compress Prompts with Gist Tokenscited by 390
  35. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 376
  36. 2024StruQ: Defending Against Prompt Injection with Structured Queriescited by 375
  37. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 369
  38. 2023RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generationcited by 367

50 most cited of 150 All 150 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Scope3Trace: Evidence-Based Identification and Extraction of Scope 3 GHG Emissions from Sustainability Reportscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Breaking the Evaluation Paradox: Evaluating High-Entropy Search with Computationally Irreducible Constraints
  2. 2025Less is More: Denoising Knowledge Graphs For Retrieval Augmented Generation
  3. 2025Magic Mushroom: A Customizable Benchmark for Fine-grained Analysis of Retrieval Noise Erosion in RAG Systems
  4. 2025Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation
  5. 2026Self-Augmenting Retrieval for Diffusion Language Models
  6. 2026Unlocking the Potentials of Retrieval-Augmented Generation for Diffusion Language Models
  7. 2026Over-Searching in Search-Augmented Large Language Models
  8. 2026Mitigating LLM Hallucinations through Domain-Grounded Tiered Retrieval