mlsanityData to 7 Oct 2026

KBM: Delineating Knowledge Boundary for Adaptive Retrieval in Large Language Models

arXiv 2411.06207 ↗First posted 9 Nov 2024cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) often struggle with dynamically changing knowledge and handling unknown static information. Retrieval-Augmented Generation (RAG) is employed to tackle these challenges and has a significant impact on improving LLM performance. In fact, we find that not all questions need to trigger RAG. By retrieving parts of knowledge unknown to the LLM and allowing the LLM to answer the rest, we can effectively reduce both time and computational costs. In our work, we propose a Knowledge Boundary Model (KBM) to express the known/unknown of a given question, and to determine whether a RAG needs to be triggered. Experiments conducted on 11 English and Chinese datasets illustrate that the KBM effectively delineates the knowledge boundary, significantly decreasing the proportion of retrievals required for optimal end-to-end performance. Furthermore, we evaluate the effectiveness of KBM in three complex scenarios: dynamic knowledge, long-tail static knowledge, and multi-hop problems, as well as its functionality as an external LLM plug-in.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 28 references that are in the map. First posted on arXiv 9 Nov 2024.

Builds on

22 of 28 references.

References · 22

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  4. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  5. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,114
  6. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  7. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  8. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
  9. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,278
  10. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 946
  11. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 452
  12. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 437
10 more
  1. 2023FreshLLMs: Refreshing Large Language Models with Search Engine Augmentationcited by 308
  2. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 275
  3. 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 146
  4. 2023The Troubling Emergence of Hallucination in Large Language Models -- An Extensive Definition, Quantification, and Prescriptive Remediationscited by 130
  5. 2024ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidencecited by 109
  6. 2024Unfamiliar Finetuning Examples Control How Language Models Hallucinatecited by 85
  7. 2023Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluationcited by 52
  8. 2023Uncertainty in Natural Language Processing: Sources, Quantification, and Applicationscited by 44
  9. 2024Teaching Large Language Models to Express Knowledge Boundary from Their Own Signalscited by 32
  10. 2024Know the Unknown: An Uncertainty-Sensitive Method for LLM Instruction Tuningcited by 16

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home
  2. 2024CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models
  3. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
  4. 2024On the Role of Long-tail Knowledge in Retrieval Augmented Large Language Models
  5. 2024Retrieval-Augmented Generation for Natural Language Processing: A Survey
  6. 2025Dynamic and Parametric Retrieval-Augmented Generation
  7. 2024Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks
  8. 2025Retrieval Feedback Memory Enhancement Large Model Retrieval Generation Method