mlsanityData to 7 Oct 2026

Harnessing Reasoning Trajectories for Hallucination Detection via Answer-agreement Representation Shaping

arXiv 2601.17467 ↗First posted 24 Jan 2026cs.LGcited by 0

On the map: LLM reasoning → Hallucination detection and mitigation

Abstract (arXiv)

Large reasoning models (LRMs) often generate long, seemingly coherent reasoning traces yet still produce incorrect answers, making hallucination detection challenging. Although trajectories contain useful signals, directly using trace text or vanilla hidden states for detection is brittle: traces vary in form and detectors can overfit to superficial patterns rather than answer validity. We introduce Answer-agreement Representation Shaping (ARS), which learns detection-friendly trace-conditioned representations by explicitly encoding answer stability. ARS generates counterfactual answers through small latent interventions, specifically, perturbing the trace-boundary embedding, and labels each perturbation by whether the resulting answer agrees with the original. It then learns representations that bring answer-agreeing states together and separate answer-disagreeing ones, exposing latent instability indicative of hallucination risk. The shaped embeddings are plug-and-play with existing embedding-based detectors and require no human annotations during training. Experiments demonstrate that ARS consistently improves detection and achieves substantial gains over strong baselines. Code is available at: https://github.com/radiolab-ntu/ars_icml2026.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning. Builds on 39 of its 46 references that are in the map. First posted on arXiv 24 Jan 2026.

Builds on

39 of 46 references.

Closest ancestors · 6

Same direction, newest first

  1. 2026Hallucination Detection and Mitigation in Large Language Models14 Jan
  2. 2026Streaming Hallucination Detection in Long Chain-of-Thought Reasoning5 Jan
  3. 2025Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical Evaluation20 Jun
  4. 2025Joint Evaluation of Answer and Reasoning Consistency for Hallucination Detection in Large Reasoning Models5 Jun
  5. 2025Are Reasoning Models More Prone to Hallucination?29 May
  6. 2025Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective19 May

Other references · 33

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  5. 2025Qwen3 Technical Reportcited by 8,195
  6. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  7. 2023Let's Verify Step by Stepcited by 3,598
  8. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  9. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  10. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  11. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  12. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
21 more
  1. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,196
  2. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 946
  3. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 795
  4. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  5. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 733
  6. 2022Teaching Models to Express Their Uncertainty in Wordscited by 731
  7. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  8. 2023The Internal State of an LLM Knows When It's Lyingcited by 644
  9. 2024INSIDE: LLMs' Internal States Retain the Power of Hallucination Detectioncited by 317
  10. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 286
  11. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 193
  12. 2023Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Modelscited by 147
  13. 2023Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigationcited by 123
  14. 2025Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoningcited by 101
  15. 2024HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detectioncited by 96
  16. 2024Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Modelscited by 84
  17. 2025T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scalingcited by 77
  18. 2023Self-Evaluation Improves Selective Generation in Large Language Modelscited by 74
  19. 2025Steer LLM Latents for Hallucination Detectioncited by 49
  20. 2024Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Modelscited by 44
  21. 2024LLM-Based Multi-Hop Question Answering with Knowledge Graph Integration in Evolving Environmentscited by 18

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Sanity Checks for Long-Form Hallucination Detection
  2. 2026Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models
  3. 2026Detecting Hallucinations in Retrieval-Augmented Generation through Grounding-Aware Sensitivity by Perturbation (GASP)
  4. 2025Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinations
  5. 2024Pelican: Correcting Hallucination in Vision-LLMs via Claim Decomposition and Program of Thought Verification
  6. 2026The First Token Knows: Single-Decode Confidence for Hallucination Detection
  7. 2025Hallucination Detection via Internal States and Structured Reasoning Consistency in Large Language Models
  8. 2026Zero-source LLM Hallucination Detection with Human-like Criteria Probing