mlsanityData to 7 Oct 2026

Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMs

arXiv 2402.10612 ↗First posted 16 Feb 2024cs.CLcited by 27

On the map: Retrieval-augmented generation → Hallucination detection in RAG

Abstract (arXiv)

Hallucinations present a significant challenge for large language models (LLMs). The utilization of parametric knowledge in generating factual content is constrained by the limited knowledge of LLMs, potentially resulting in internal hallucinations. While incorporating external information can help fill knowledge gaps, it also introduces the risk of irrelevant information, thereby increasing the likelihood of external hallucinations. To balance the use of parametric knowledge within LLMs and external information, in this study, we present Rowen, a novel framework that enhances LLMs with an adaptive retrieval augmentation process tailored to address hallucinated outputs. Rowen introduces a consistency-based hallucination detection module, which assesses the model's uncertainty regarding the input query by evaluating the semantic inconsistencies in various responses generated across different languages or models. When high uncertainties in the responses are detected, Rowen activates the retrieval of external information to rectify the model outputs. Through comprehensive empirical experiments, we demonstrate that Rowen surpasses the current state-of-the-art in both detecting and mitigating hallucinated content within the outputs of LLMs.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Placed in Hallucination detection in RAG, one of 15 directions in Retrieval-augmented generation. Builds on 21 of its 43 references that are in the map. First posted on arXiv 16 Feb 2024.

Builds on

21 of 43 references.

References · 21

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  5. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  6. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  7. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  8. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  9. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  10. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  11. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  12. 2023Active Retrieval Augmented Generationcited by 506
9 more
  1. 2023FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarioscited by 247
  2. 2023A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generationcited by 202
  3. 2022Large Language Models with Controllable Working Memorycited by 169
  4. 2023LM vs LM: Detecting Factual Errors via Cross Examinationcited by 155
  5. 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 146
  6. 2023Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Frameworkcited by 139
  7. 2023Do Language Models Know When They're Hallucinating References?cited by 115
  8. 2023SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistencycited by 89
  9. 2023Towards Alleviating the Object Bias in Prompt Tuning-based Factual Knowledge Extractioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 12; 2026: 7.

27 papers.

Sort:

By area:

  1. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  2. 2024Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wiselycited by 65
  3. 2024RATT: A Thought Structure for Coherent and Correct LLM Reasoningcited by 39
  4. 2024ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Modelscited by 28
  5. 2025UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularitiescited by 18
  6. 2024CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Controlcited by 13
  7. 2026Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewardscited by 13
  8. 2024MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Modelscited by 11
  9. 2024A Theory for Token-Level Harmonization in Retrieval-Augmented Generationcited by 7
  10. 2026Adaptive Stopping for Multi-Turn LLM Reasoningcited by 7
  11. 2026To Call or Not to Call: A Framework to Assess and Optimize LLM Tool Callingcited by 7
  12. 2025Rethinking Retrieval-Augmented Generation for Medicine: A Large-Scale, Systematic Expert Evaluation and Practical Insightscited by 6
15 more
  1. 2025Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval Augmented Generationcited by 5
  2. 2024Enhancing Tourism Recommender Systems for Sustainable City Trips Using Retrieval-Augmented Generationcited by 4
  3. 2025Uncertainty-o: One Model-agnostic Framework for Unveiling Uncertainty in Large Multimodal Modelscited by 4
  4. 2025Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILEcited by 4
  5. 2026How You Ask Matters! Adaptive RAG Robustness to Query Variationscited by 3
  6. 2025Retrieval-augmented Decoding for Improving Truthfulness in Open-ended Generationcited by 2
  7. 2025Fast, Slow, and Tool-augmented Thinking for LLMs: A Reviewcited by 2
  8. 2024Review-Then-Refine: A Dynamic Framework for Multi-Hop Question Answering with Temporal Adaptabilitycited by 1
  9. 2025Addressing the sustainable AI trilemma: a case study on LLM agents and RAGcited by 1
  10. 2025GE-Chat: A Graph Enhanced RAG Framework for Evidential Response Generation of LLMscited by 1
  11. 2025Chain or tree? Re-evaluating complex reasoning from the perspective of a matrix of thoughtcited by 1
  12. 2026Twin Worlds: Equivariance-Based Abstention for Evidence-Grounded Reasoningcited by 1
  13. 2026Return or Revise? Learning When Revision Helps Retrieval-Augmented QAcited by 1
  14. 2025Iterative Tree Analysis for Medical Criticscited by 0
  15. 2026From Sequence to Structure: Relational Uncertainty Propagation for LLM Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025AutoRAG-LoRA: Hallucination-Triggered Knowledge Retuning via Lightweight Adapters
  2. 2024ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability
  3. 2025Theoretical Foundations and Mitigation of Hallucination in Large Language Models
  4. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
  5. 2025LUMINA: Detecting Hallucinations in RAG System with Context-Knowledge Signals
  6. 2025MALM: A Multi-Information Adapter for Large Language Models to Mitigate Hallucination
  7. 2024THaMES: An End-to-End Tool for Hallucination Mitigation and Evaluation in Large Language Models
  8. 2025Hybrid Retrieval for Hallucination Mitigation in Large Language Models: A Comparative Analysis