mlsanityData to 7 Oct 2026

Hallucination detection and mitigation

157 papers1 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: hallucination, hallucinations, hallucination detection, detection, mitigating

Key facts. Hallucination detection and mitigation: 157 papers on arXiv since 2022 (data through 7 Oct 2026). 7 of its 157 mapped papers (4%) cite “More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models” (2025, arXiv 2505.21523). 6 of its 157 mapped papers (4%) cite “Are Reasoning Models More Prone to Hallucination?” (2025, arXiv 2505.23646). 6 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

6 new papers, 17 Sep – 7 Oct; 1 this week.

  1. This week · 1
  2. PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMs
  3. Earlier · 5
  4. Hallucination Across the Reasoning Lifecycle: Interface Visibility, Causal Evidence, and Release Control in Large Reasoning Models
  5. External Observers May See More Clearly: Cross-Model Span-Level Hallucination Detection in Large Language Models via Hidden State Probing
  6. Alleviating Hallucination in Reasoning Tasks with Training-Free Uncertainty-Guided Steering
  7. Beneath the Scores: Rethinking Hallucination Evaluation for Video Understanding Models
  8. DEEPO: Dual-Entropy Enhanced Policy Optimization for Hallucination in MLLMs

Foundations

Most cited by papers here

  1. More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models2025cited by 7 here
  2. Are Reasoning Models More Prone to Hallucination?2025cited by 6 here
  3. Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective2025cited by 5 here
  4. Medical Hallucinations in Foundation Models and Their Impact on Healthcare2025cited by 4 here
  5. MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM2025cited by 4 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 40 here
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 21 here
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 5 here
  4. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 7 here
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 8 here
  6. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 10 here
  7. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 22 here
  8. 2025Are Reasoning Models More Prone to Hallucination?cited by 6 here
16 more it builds on, not in this chain
  1. 2017Proximal Policy Optimization Algorithmscited by 5 here
  2. 2022Large Language Models are Zero-Shot Reasonerscited by 11 here
  3. 2022Language Models (Mostly) Know What They Knowcited by 14 here
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 6 here
  5. 2023Multimodal Chain-of-Thought Reasoning in Language Modelscited by 7 here
  6. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 5 here
  7. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7 here
  8. 2023Let's Verify Step by Stepcited by 9 here
  9. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 6 here
  10. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contextscited by 7 here
  11. 2023Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotationscited by 5 here
  12. 2024OpenAI o1 System Cardcited by 10 here
  13. 2024DeepSeek-V3 Technical Reportcited by 10 here
  14. 2025R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalizationcited by 6 here
  15. 2025Qwen3 Technical Reportcited by 15 here
  16. 2025More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Modelscited by 7 here

The 24 most cited of 504.

Browse

30 of 157, ranked 6–35

  1. 6Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical Evaluation20254
  2. 7Auditing Meta-Cognitive Hallucinations in Reasoning Large Language Models20253
  3. 8Joint Evaluation of Answer and Reasoning Consistency for Hallucination Detection in Large Reasoning Models20253
  4. 9Streaming Hallucination Detection in Long Chain-of-Thought Reasoning20262
  5. 10Hallucination Detection and Mitigation in Large Language Models20262
  6. 11HalluGuard: Demystifying Data-Driven and Reasoning-Driven Hallucinations in LLMs20262
  7. 12Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning Models20252
  8. 13Mitigating Object Hallucination via Concentric Causal Attention20242
  9. 14Combating Multimodal LLM Hallucination via Bottom-Up Holistic Reasoning20242
  10. 15Harnessing Reasoning Trajectories for Hallucination Detection via Answer-agreement Representation Shaping20261
All 30
  1. 16Understanding and Mitigating Hallucinations in Multimodal Chain-of-Thought Models20261
  2. 17Beyond the Global Scores: Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinations20261
  3. 18When Looking Is Not Enough: Visual Attention Structure Reveals Hallucination in MLLMs20261
  4. 19Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking20251
  5. 20Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Models20251
  6. 21Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation20251
  7. 22Decoupling Contrastive Decoding: Robust Hallucination Mitigation in Multimodal Large Language Models20251
  8. 23The Hallucination Tax of Reinforcement Finetuning20251
  9. 24CLATTER: Comprehensive Entailment Reasoning for Hallucination Detection20251
  10. 25HalluRNN: Mitigating Hallucinations via Recurrent Cross-Layer Reasoning in Large Vision-Language Models20251
  11. 26KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality20251
  12. 27Learning to Reason for Factuality20251
  13. 28Unsupervised Hallucination Detection by Inspecting Reasoning Processes20251
  14. 29HARP: Hallucination Detection via Reasoning Subspace Projection20251
  15. 30D2HScore: Reasoning-Aware Hallucination Detection via Semantic Breadth and Depth Analysis in LLMs20251
  16. 31HalluGuard: Evidence-Grounded Small Reasoning Models to Mitigate Hallucinations in Retrieval-Augmented Generation20251
  17. 32Mitigating Hallucination in Large Language Models (LLMs): An Application-Oriented Survey on RAG, Reasoning, and Agentic Systems20251
  18. 33Hallucinate Less by Thinking More: Aspect-Based Causal Abstention for Large Language Models20251
  19. 34Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning20241
  20. 35FG-PRM: Fine-grained Hallucination Detection and Mitigation in Language Model Mathematical Reasoning20241