mlsanityData to 7 Oct 2026

CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control

arXiv 2405.18727 ↗First posted 29 May 2024cs.CL cs.AI cs.IRcited by 13

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

Abstract (arXiv)

Retrieval-augmented generation (RAG) has emerged as a promising solution for mitigating hallucinations of large language models (LLMs) with retrieved external knowledge. Adaptive RAG enhances this approach by enabling dynamic retrieval during generation, activating retrieval only when the query exceeds LLM's internal knowledge. Existing methods primarily focus on detecting LLM's confidence via statistical uncertainty. Instead, we present the first attempts to solve adaptive RAG from a representation perspective and develop an inherent control-based framework, termed name. Specifically, we extract the features that represent the honesty and confidence directions of LLM and adopt them to control LLM behavior and guide retrieval timing decisions. We also design a simple yet effective query formulation strategy to support adaptive retrieval. Experiments show that name is superior to existing adaptive RAG methods on a diverse set of tasks, the honesty steering can effectively make LLMs more honest and confidence monitoring is a promising indicator of retrieval trigger.Our code is available at urlhttps://github.com/HSLiu-Initial/CtrlA.

Key facts. Cited by 13 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 58 of its 67 references that are in the map. First posted on arXiv 29 May 2024.

Builds on

58 of 67 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation31 Mar
  2. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity21 Mar
  3. 2024RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering26 Feb
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 54

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  5. 2023Mistral 7Bcited by 3,065
  6. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  7. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  8. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  9. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  10. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  11. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,259
  12. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,239
38 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. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 946
  4. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  5. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  6. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 795
  7. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  8. 2023AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedbackcited by 738
  9. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  10. 2023The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasetscited by 673
  11. 2023The Internal State of an LLM Knows When It's Lyingcited by 644
  12. 2023Enabling Large Language Models to Generate Text with Citationscited by 584
  13. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 556
  14. 2023Active Retrieval Augmented Generationcited by 506
  15. 2022Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskcited by 417
  16. 2023DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Modelscited by 367
  17. 2024INSIDE: LLMs' Internal States Retain the Power of Hallucination Detectioncited by 317
  18. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 316
  19. 2023FreshLLMs: Refreshing Large Language Models with Search Engine Augmentationcited by 308
  20. 2023Do Large Language Models Know What They Don't Know?cited by 238
  21. 2022ASQA: Factoid Questions Meet Long-Form Answerscited by 231
  22. 2021Internet-Augmented Dialogue Generationcited by 217
  23. 2024Corrective Retrieval Augmented Generationcited by 187
  24. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  25. 2023Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Frameworkcited by 139
  26. 2023Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sourcescited by 121
  27. 2019A Discrete Hard EM Approach for Weakly Supervised Question Answeringcited by 78
  28. 2023Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblockscited by 77
  29. 2023Self-Knowledge Guided Retrieval Augmentation for Large Language Modelscited by 69
  30. 2024DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Modelscited by 63
  31. 2024When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentationcited by 59
  32. 2024Linguistic Calibration of Long-Form Generationscited by 59
  33. 2023Query Expansion by Prompting Large Language Modelscited by 56
  34. 2023The Curious Case of Hallucinatory (Un)answerability: Finding Truths in the Hidden States of Over-Confident Large Language Modelscited by 54
  35. 2024When to Trust LLMs: Aligning Confidence with Response Qualitycited by 42
  36. 2022MAUVE Scores for Generative Models: Theory and Practicecited by 34
  37. 2024Self-DC: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questionscited by 30
  38. 2023Improving the Reliability of Large Language Models by Leveraging Uncertainty-Aware In-Context Learningcited by 29

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 8; 2026: 5.

13 papers.

Sort:

By area:

  1. 2025RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discoverycited by 19
  2. 2025HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generationcited by 9
  3. 2025Test-time Corpus Feedback: From Retrieval to RAGcited by 3
  4. 2025HetaRAG: Hybrid Deep Retrieval-Augmented Generation across Heterogeneous Data Storescited by 3
  5. 2026SHIFT: Gate-Modulated Activation Steering for Knowledge Conflict Mitigation in Retrieval-Augmented Generationcited by 3
  6. 2025Think Right, Not More: Test-Time Scaling for Numerical Claim Verificationcited by 2
  7. 2025Fine-Grained Emotion Recognition via In-Context Learningcited by 2
  8. 2025MedAI: Evaluating TxAgent's Therapeutic Agentic Reasoning in the NeurIPS CURE-Bench Competitioncited by 2
  9. 2026SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Searchcited by 2
  10. 2025Memory-Aware and Uncertainty-Guided Retrieval for Multi-Hop Question Answeringcited by 1
  11. 2026Rethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Rankingcited by 0
  12. 2026When Retrieval Helps: Selective Retrieval for Single-Turn Mental-Health QAcited by 0
1 more
  1. 2026BELIEFRAG: Making Adaptive RAG State-Aware under Evolving Evidencecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025LLM-Independent Adaptive RAG: Let the Question Speak for Itself
  2. 2025Fast or Better? Balancing Accuracy and Cost in Retrieval-Augmented Generation with Flexible User Control
  3. 2025Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home
  4. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
  5. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
  6. 2025Investigating the Robustness of Retrieval-Augmented Generation at the Query Level
  7. 2025Dynamic and Parametric Retrieval-Augmented Generation
  8. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers