mlsanityData to 7 Oct 2026

Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home

arXiv 2501.12835 ↗First posted 22 Jan 2025cs.CL cs.LGcited by 33

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

Abstract (arXiv)

Retrieval Augmented Generation (RAG) improves correctness of Question Answering (QA) and addresses hallucinations in Large Language Models (LLMs), yet greatly increase computational costs. Besides, RAG is not always needed as may introduce irrelevant information. Recent adaptive retrieval methods integrate LLMs' intrinsic knowledge with external information appealing to LLM self-knowledge, but they often neglect efficiency evaluations and comparisons with uncertainty estimation techniques. We bridge this gap by conducting a comprehensive analysis of 35 adaptive retrieval methods, including 8 recent approaches and 27 uncertainty estimation techniques, across 6 datasets using 10 metrics for QA performance, self-knowledge, and efficiency. Our findings show that uncertainty estimation techniques often outperform complex pipelines in terms of efficiency and self-knowledge, while maintaining comparable QA performance.

Key facts. Cited by 33 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 36 of its 53 references that are in the map. First posted on arXiv 22 Jan 2025.

Builds on

36 of 53 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity21 Mar
  2. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 34

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  7. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  8. 2024Qwen2 Technical Reportcited by 2,076
  9. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  10. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  11. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  12. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
22 more
  1. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  2. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  3. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  4. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  5. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  6. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  7. 2023Physics of Language Models: Part 3.1, Knowledge Storage and Extractioncited by 264
  8. 2020Unsupervised Quality Estimation for Neural Machine Translationcited by 210
  9. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 193
  10. 2024Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantificationcited by 159
  11. 2016Eigenvalues of the Hessian in Deep Learning: Singularity and Beyondcited by 156
  12. 2018Rademacher Complexity for Adversarially Robust Generalizationcited by 132
  13. 2023LM-Polygraph: Uncertainty Estimation for Language Modelscited by 130
  14. 2023Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Taskscited by 73
  15. 2022Mutual Information Alleviates Hallucinations in Abstractive Summarizationcited by 67
  16. 2024When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentationcited by 59
  17. 2022On the Maximum Hessian Eigenvalue and Generalizationcited by 57
  18. 2024Learning to Edit: Aligning LLMs with Knowledge Editingcited by 43
  19. 2024When to Trust LLMs: Aligning Confidence with Response Qualitycited by 42
  20. 2024Benchmarking Knowledge Boundary for Large Language Models: A Different Perspective on Model Evaluationcited by 37
  21. 2022Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Datacited by 21
  22. 2024Constructing Benchmarks and Interventions for Combating Hallucinations in LLMscited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 13; 2026: 20.

33 papers.

Sort:

By area:

  1. 2025Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Modelscited by 17
  2. 2025Reconsidering LLM Uncertainty Estimation Methods in the Wildcited by 17
  3. 2025Query-Level Uncertainty in Large Language Modelscited by 12
  4. 2025Self-Routing RAG: Binding Selective Retrieval with Knowledge Verbalizationcited by 9
  5. 2025LLM-Independent Adaptive RAG: Let the Question Speak for Itselfcited by 7
  6. 2026To Call or Not to Call: A Framework to Assess and Optimize LLM Tool Callingcited by 7
  7. 2026LLMs Should Express Uncertainty Explicitlycited by 6
  8. 2025RGAR: Recurrence Generation-augmented Retrieval for Factual-aware Medical Question Answeringcited by 5
  9. 2025Self-Taught Self-Correction for Small Language Modelscited by 5
  10. 2025Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval Augmented Generationcited by 5
  11. 2025Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QAcited by 5
  12. 2025Uncertainty Quantification for Retrieval-Augmented Reasoningcited by 5
21 more
  1. 2026NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG Systemscited by 5
  2. 2025Do LVLMs Know What They Know? A Systematic Study of Knowledge Boundary Perception in LVLMscited by 3
  3. 2026How You Ask Matters! Adaptive RAG Robustness to Query Variationscited by 3
  4. 2026Evaluating Confidence-Gated Retrieval with Matched Trajectory Replaycited by 3
  5. 2025Fast, Slow, and Tool-augmented Thinking for LLMs: A Reviewcited by 2
  6. 2026HALT: Verification-Aware Stopping for Retrieval-Augmented Search Agentscited by 2
  7. 2025Optimizing Retrieval for RAG via Reinforcement Learningcited by 1
  8. 2026Leveraging LLM Parametric Knowledge for Fact Checking without Retrievalcited by 1
  9. 2026Pre-Generation Hallucination Detection in Large Language Models via Soft-Target Attention Probingcited by 1
  10. 2026When Reranking Hurts: Uncertainty-Based Gating for Few-Shot Rerankingcited by 1
  11. 2026Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimationcited by 1
  12. 2026Return or Revise? Learning When Revision Helps Retrieval-Augmented QAcited by 1
  13. 2026Evolutionary Search for Automated Design of Uncertainty Quantification Methodscited by 0
  14. 2026ICICLE: Expanding Retrieval with In-Context Documentscited by 0
  15. 2026Evaluating the Relevance of Uncertainty Estimators for LLM Hallucinationcited by 0
  16. 2026When Depth Is Better Told Than Shown: Depth-Ordinal Prompting for Vision-Language Spatial Reasoningcited by 0
  17. 2026LODESTAR: Robust Entropy-Based Answer Selection in Retrieval-Augmented Generation for Question Answering -- Directing Frozen-LLM Entropy with a Reinforcement-Learned Prompt Polarizer under Misleading Passagescited by 0
  18. 2026From Sequence to Structure: Relational Uncertainty Propagation for LLM Agentscited by 0
  19. 2026Before Answering: Evidence Sufficiency under Size-Matched Memory Constructioncited by 0
  20. 2026Relevance Is Not Sufficient Evidence: Detecting Evidence Gaps Before Generation in RAGcited by 0
  21. 2026BELIEFRAG: Making Adaptive RAG State-Aware under Evolving Evidencecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Interpretable Uncertainty for Adaptive Retrieval and Reasoning in Question Answering
  2. 2024SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation
  3. 2025Investigating the Robustness of Retrieval-Augmented Generation at the Query Level
  4. 2024CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control
  5. 2026URAG: A Benchmark for Uncertainty Quantification in Retrieval-Augmented Large Language Models
  6. 2026AB-RAG: Adaptive Budgeted Retrieval-Augmented Generation for Reliable Question Answering
  7. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
  8. 2025Optimizing Knowledge Integration in Retrieval-Augmented Generation with Self-Selection