mlsanityData to 7 Oct 2026

Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation

arXiv 2307.11019 ↗First posted 20 Jul 2023cs.CL cs.IRcited by 146

Not on the map. Why?

Cited by 48 in Retrieval-augmented generation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Large language models (LLMs) have shown impressive prowess in solving a wide range of tasks with world knowledge. However, it remains unclear how well LLMs are able to perceive their factual knowledge boundaries, particularly under retrieval augmentation settings. In this study, we present the first analysis on the factual knowledge boundaries of LLMs and how retrieval augmentation affects LLMs on open-domain question answering (QA), with a bunch of important findings. Specifically, we focus on three research questions and analyze them by examining QA, priori judgement and posteriori judgement capabilities of LLMs. We show evidence that LLMs possess unwavering confidence in their knowledge and cannot handle the conflict between internal and external knowledge well. Furthermore, retrieval augmentation proves to be an effective approach in enhancing LLMs' awareness of knowledge boundaries. We further conduct thorough experiments to examine how different factors affect LLMs and propose a simple method to dynamically utilize supporting documents with our judgement strategy. Additionally, we find that the relevance between the supporting documents and the questions significantly impacts LLMs' QA and judgemental capabilities. The code to reproduce this work is available at https://github.com/RUCAIBox/LLM-Knowledge-Boundary.

Key facts. Cited by 146 papers in the map (data through 7 Oct 2026). Builds on 29 of its 35 references that are in the map. First posted on arXiv 20 Jul 2023.

Builds on

29 of 35 references.

References · 29

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  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. 2023A Survey of Large Language Modelscited by 2,537
  10. 2017Billion-scale similarity search with GPUscited by 2,477
  11. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  12. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
17 more
  1. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  2. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  3. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 571
  4. 2023Is ChatGPT a General-Purpose Natural Language Processing Task Solver?cited by 486
  5. 2020RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answeringcited by 410
  6. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 296
  7. 2023Do Large Language Models Know What They Don't Know?cited by 238
  8. 2021Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrievalcited by 203
  9. 2019MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehensioncited by 183
  10. 2021RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-rankingcited by 175
  11. 2022Dense Text Retrieval based on Pretrained Language Models: A Surveycited by 136
  12. 2023Evaluating Open-Domain Question Answering in the Era of Large Language Modelscited by 110
  13. 2023Automatic Evaluation of Attribution by Large Language Modelscited by 70
  14. 2021PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrievalcited by 50
  15. 2022SimANS: Simple Ambiguous Negatives Sampling for Dense Text Retrievalcited by 21
  16. 2023TOME: A Two-stage Approach for Model-based Retrievalcited by 21
  17. 2022Implicit Feedback for Dense Passage Retrieval: A Counterfactual Approachcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 20; 2024: 69; 2025: 44; 2026: 13.

146 papers.

Sort:

By area:

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  2. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  3. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  4. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  5. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  6. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  7. 2023Explainability for Large Language Models: A Surveycited by 331
  8. 2023Benchmarking Large Language Models in Retrieval-Augmented Generationcited by 307
  9. 2024Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMscited by 224
  10. 2023Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimizationcited by 223
  11. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 204
  12. 2023LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examplescited by 177
38 more
  1. 2024A Comprehensive Study of Knowledge Editing for Large Language Modelscited by 157
  2. 2023PaperQA: Retrieval-Augmented Generative Agent for Scientific Researchcited by 143
  3. 2023The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversationcited by 107
  4. 2023R-Tuning: Instructing Large Language Models to Say `I Don't Know'cited by 106
  5. 2023Graph Foundation Models: Concepts, Opportunities and Challengescited by 101
  6. 2023EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Modelscited by 97
  7. 2024Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Modelscited by 93
  8. 2024The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Modelscited by 87
  9. 2024Retrieval-Augmented Generation for Natural Language Processing: A Surveycited by 70
  10. 2024When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentationcited by 59
  11. 2025SMART: Self-Aware Agent for Tool Overuse Mitigationcited by 52
  12. 2024Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answeringcited by 51
  13. 2024Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?cited by 47
  14. 2024Can AI Assistants Know What They Don't Know?cited by 47
  15. 2024Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Eracited by 45
  16. 2024Learning to Trust Your Feelings: Leveraging Self-awareness in LLMs for Hallucination Mitigationcited by 43
  17. 2024Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflectioncited by 40
  18. 2024UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-world Document Analysiscited by 40
  19. 2024Knowledge Boundary of Large Language Models: A Surveycited by 36
  20. 2024Teaching Large Language Models to Express Knowledge Boundary from Their Own Signalscited by 32
  21. 2024Self-DC: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questionscited by 30
  22. 2025Adaptive Tool Use in Large Language Models with Meta-Cognition Triggercited by 29
  23. 2023Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applicationscited by 28
  24. 2024REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answeringcited by 28
  25. 2024Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMscited by 27
  26. 2024Discerning and Resolving Knowledge Conflicts through Adaptive Decoding with Contextual Information-Entropy Constraintcited by 27
  27. 2024Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generationcited by 27
  28. 2024Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generationcited by 25
  29. 2024BASES: Large-scale Web Search User Simulation with Large Language Model based Agentscited by 24
  30. 2024Boosting Conversational Question Answering with Fine-Grained Retrieval-Augmentation and Self-Checkcited by 24
  31. 2024Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Modelscited by 24
  32. 2024Small Language Model Can Self-correctcited by 23
  33. 2024Are Large Language Models Good at Utility Judgments?cited by 22
  34. 2024Enhancing Confidence Expression in Large Language Models Through Learning from Past Experiencecited by 21
  35. 2023Can Large Language Models Provide Security & Privacy Advice? Measuring the Ability of LLMs to Refute Misconceptionscited by 20
  36. 2024Perception of Knowledge Boundary for Large Language Models through Semi-open-ended Question Answeringcited by 20
  37. 2024Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspectivecited by 20
  38. 2024MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledgecited by 20

50 most cited of 146 All 146 (JSON)