Language Model Error Detection

Ask about this topic

Overview

Language model error detection studies how to recognize mistakes such as hallucinated facts, faulty reasoning, incorrect code or tool calls, and errors in specialized domains. Methods use output signals such as token probabilities, entropy, and agreement across samples or models, as well as internal activations, probes, retrieval, execution tests, and formal verifiers. Benchmarks span question answering, mathematical reasoning, coding, clinical and legal tasks, and multilingual settings, but results can be distorted by benchmark artifacts or fail to transfer across models and domains. A central challenge is that detecting an error does not ensure that a system can correct it: confident mistakes may be hard to observe, while interventions can introduce new errors.

Latest papers

CardsList

91 papers21 papers in the last four weeks, up 110% on the four weeks before. 0.1% of all new papers.

  1. INVAR-Agri: Detecting Discrepancies in Multilingual Operator Manuals of Agricultural Implements with a Fine-Tuned LLM

    Oct 26, 2026Timo OksanenLanguage Model Error DetectionDocument Understanding

    Technical University of Munich, Germany; Chair of Agrimechatronics; Munich Institute of Robotics and Machine Intelligence (MIRMI)

  2. Models Verify Sufficiency, Not Validity: Usable Falsehoods Evade the Checks that Gaps Trigger

    Oct 25, 2026Naveen MadirajuLLM ReliabilityLanguage Model Reasoning Evaluation

    Google, San Jose, CA, USA

  3. Why Does Structured Output Fail? An Empirical Study of Prompt-Enforced Pydantic Schemas Across Nine LLMs

    Oct 24, 2026Amit VermaSchema-Constrained GenerationLLM Reliability

    Independent Researcher, Phoenix, AZ, USA.

  4. Adaptive Transfer of Representational Signatures for LLM Reliability Detection

    Oct 24, 2026Yongtong Li, Yixuan Florence Wu, Jiawei Zhang +1Language Model Error DetectionLLM Reliability

    Northwestern University · University of Wisconsin–Madison

  5. Detection Is Not Enough: Reasoning Traces as Testable Program Hypotheses

    Oct 21, 2026Vaidehi HegdeLanguage Model Reasoning EvaluationLanguage Model Error Detection

    Indian Institute of Technology (Indian School of Mines) Dhanbad

  6. B-CARE: Blind Classwise Assessment of Relative Evidence for Stance Error Ranking

    Oct 21, 2026Meysam Sabbaghan, Doina CarageaLanguage Model Error DetectionStance Detection

    Department of Computer Science, Kansas State University

  7. Detecting Errors in Large Language Model Responses: The Incremental Predictive Value of Hidden States

    Oct 20, 2026Ningzhi Li, Xiaojun Ma, Xiaofei WangLanguage Model Error DetectionLLM Hallucination Detection

    Beijing Institute of Computer Technology and Application, Beijing, China

  8. Learning When to Abort in Transformer Planning: A Mechanistic Study

    Oct 18, 2026Shi Feng, Qimin Zhong, Siwei Wang +4Language Model Error DetectionTransformer Interpretability

    Harvard University · Shenzhen University · Microsoft Research Asia +1

  9. Self-Guided LLM Reasoning for Error Diagnosis in Vehicle Routing Problems

    Oct 15, 2026Ni Zhang, Jianan Zhou, Yue-Jiao Gong +1Language Model Error DetectionVehicle Routing

    Singapore Management University · Nanyang Technological University · South China University of Technology

  10. Attention-Graph Curvature for the Verification of Mathematical Reasoning

    Oct 12, 2026Kanghyeon Kim, Johannes F. Lutzeyer, Yanzhu GuoLanguage Model Error DetectionReasoning Verification

    Télécom Paris, IPP · LIX, CNRS, École Polytechnique, IPP

  11. Phantom Merge: When Your Large Language Model Agents Pick One but Tell You About Another

    Oct 12, 2026Wangshu Zhu, Qianwen Guo, Yushun DongLLM GroundingLLM Agent Reliability

    Department of Computer Science, Florida State University · Department of Civil and Environmental Engineering, FAMU–FSU College of Engineering

  12. Where Did We Go Wrong? Localizing Errors to Repair Multi-Turn Conversations

    Oct 10, 2026Alessandro Morosini, Wei Sun, Georgia PerakisState TrackingLanguage Model Error Detection

    Massachusetts Institute of Technology · IBM Research

  13. Deception by Omission: Language Models Knowingly Hide Their Mistakes

    Oct 8, 2026Lucas Florin, Amelie Knecht, Ulysse Schaller +1Deception in Language ModelsLanguage Model Error Detection

    AI Safety Research Group, University of Stuttgart, Germany

  14. Beyond Imitation: A Framework and Benchmark for LLM-Assisted Peer Review

    Oct 8, 2026Rachel S. Y. Teo, Yutaro Yamada, Shashank Kotyan +2Automated Peer ReviewLLM Evaluation

    Sakana AI · National University of Singapore

  15. Learning from Failures: A Failure-Driven Prompt Refinement for LLM-Based Vulnerability Analysis

    Oct 6, 2026Mandana Ghadamian, David MohaisenLLMs for CybersecuritySoftware Vulnerability Detection

    University of Central Florida, Orlando, FL 32816, USA

  16. Language models can notice an impossible engineering problem yet still report it as solved

    Oct 5, 2026Shaoliang Yang, Jun WangNumerical Reasoning in Language ModelsLanguage Model Error Detection

    Santa Clara University Santa Clara, CA 95053, USA

  17. Understanding Errors in LLM-Based Question Answering over Imperfect Tables

    Oct 3, 2026Baowen Zhang, Wei Fan, Ruman Wang +1Table QALanguage Model Error Detection

    University of Wisconsin–Madison · University of Auckland, Auckland, New Zealand · Liaoning Provincial People’s Hospital +1

  18. When Does a Second Model Help? Cross-Model Review in LLM Verification

    Oct 1, 2026Tae-Eun SongLLM EvaluationLanguage Model Error Detection

    Daejeon Jungang Cheonggua Co., Ltd.

  19. Locating Answer-Correctness Signals in Frozen Large Language Models

    Sep 29, 2026Yuansen Liu, Yixuan Tang, Anthony Kum Hoe TungLLM Answer VerificationLanguage Model Error Detection

    School of Computing, National University of Singapore

  20. SemOPT: Fixing Semantic Errors in LLM-based Optimization Modeling via Reward-Guided Search

    Sep 29, 2026Zetong Zhou, Wentao Zhang, Jingyuan Wang +3Language Model Error DetectionLarge Language Model-Guided Optimization

    School of Computer Science and Engineering, Beihang University, Beijing, China · MIIT Key Laboratory of Data and Decision Intelligence, Beihang University, Beijing, China · School of Data Science, The Chinese University of Hong Kong, Shenzhen, China +1

  21. Spontaneous Context Restoration: How Language Models Recover from Corrupted Inputs

    Sep 28, 2026Pranjal Garg, Jacob BeckLanguage Model Error DetectionMechanistic Interpretability

    Independent Researcher

  22. On the Limits of Metacognitive Monitoring in LLMs

    Sep 28, 2026Dongqi Han, Yifan Yang, Dongsheng LiLanguage Model Error DetectionConfidence Estimation in Language Models

    Microsoft Research Asia

  23. Quizzing the Translation: A Prover-Grounded Evaluation Metric for NL→\rightarrowFOL

    Sep 27, 2026Pu Suo, Ali EmamiLanguage Model Error DetectionMathematical Reasoning

    Emory University

  24. The Error You See Is Not the Error You Made: Progression-aware Reasoning Origin for Reasoning Error Localization

    Sep 27, 2026Yiguo Wang, Ziyuan Yang, Yi Zou +3Language Model Error DetectionReasoning Verification

    Xiaopeng Honors College, Nanchang Hangkong University, China · School of Cyber Science and Engineering, Sichuan University, China · School of Software, Nanchang Hangkong University, China +1

  25. Prioritizing Repeated LLM Evaluation for Hidden Failure Discovery

    Sep 26, 2026Keita Broadwater, Akin BroadwaterLLM EvaluationLLM Reliability

    Independent Researcher San Jose, CA USA · Bellarmine College Prepatory San Jose, CA USA

  26. Pinocchio: Fast Uncertainty Estimates for Black-Box Language Models

    Sep 21, 2026Kevin David Hayes, Arka Pal, Haosong Zhang +2Language Model Error DetectionConfidence Estimation in Language Models

    Department of Computer Science, University of Maryland · Ritual AI · Fudan University +1

  27. Correct Diagnosis, Better Feedback: A Symbolic-Verifier for Faithful LLM Tutoring Feedback in Logic Proofs

    Sep 18, 2026Tahreem Yasir, Arnav Mody, Xioayi Tian +1Intelligent Tutoring SystemsLanguage Model Error Detection

    North Carolina State University · Purdue University · Kennesaw State University

  28. Look Before You Leap: Factual Decoding with Internal Attribution Signals

    Sep 14, 2026Hayeong Ryu, JungMin Yun, Byeonggeuk Lim +2Language Model DecodingLanguage Model Error Detection

    Department of Artificial Intelligence, Chung-Ang University · Graduate School of Advanced Imaging Sciences, Multimedia and Film, Chung-Ang University

  29. When the Wrong Key Wins: Understanding and Detecting Hallucinations in LLMs

    Sep 14, 2026Xuhan Tong, Haoyue Bai, Dawei Zhou +2Language Model Error DetectionHallucination in Language Models

    University of Wisconsin–Madison

  30. Domain-Specific Hallucination Detection in Large Language Models

    Sep 10, 2026Varun Teja Chundru, Debasmita BiswasLanguage Model Error DetectionLLM Hallucination Mitigation

    Department of Computer Science Purdue University Fort Wayne