Confidence Estimation in Language Models

Ask about this topic

Overview

The field studies whether language models can tell when their answers are likely to be wrong, which matters for deciding when to answer, abstain, retrieve evidence, or spend more computation. Methods include verbalized confidence, token probabilities and sampling-based agreement, as well as hidden-state probes, activation signals, post-hoc calibration, and conformal prediction. These approaches are tested across settings such as factual question answering, mathematical reasoning, code generation, multilingual tasks, and tool-using agents. A central challenge is that confidence signals can disagree or shift with prompts, training, and distribution changes; good calibration or error ranking alone does not guarantee useful decisions or reliable risk guarantees.

Latest papers

CardsList

249 papers45 papers in the last four weeks, up 96% on the four weeks before. 0.3% of all new papers.

  1. Process Supervision of Confidence Margin for Calibrated LLM Reasoning

    Apr 25, 2026Liaoyaqi Wang, Chunsheng Zuo, William Jurayj +2Confidence Estimation in Language ModelsRL for Language Model Reasoning

    Johns Hopkins University

  2. How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals

    Apr 24, 2026Dharshan Kumaran, Viorica Patraucean, Simon Osindero +2LLM Self-CorrectionLanguage Model Error Detection

    Google DeepMind · Princeton University

  3. Calibration Drift Under Reasoning: How Chain-of-Thought Budgets Induce Overconfidence in Large Language Models

    Apr 24, 2026Prakul Sunil Hiremath, Harshit R. HiremathConfidence Estimation in Language ModelsCoT Reasoning

    Department of Computer Science and Engineering Visvesvaraya Technological University, Belagavi · Department of Computer Science and Business System SG Balekundri Institute of Technology, Belagavi

  4. Verbal Confidence Saturation in 3-9B Open-Weight Instruction-Tuned LLMs: A Pre-Registered Psychometric Validity Screen

    Apr 24, 2026Jon-Paul CacioliLLM EvaluationConfidence Estimation in Language Models

    Independent Researcher, Melbourne, Australia

  5. Binary Agreement for Efficient Unsupervised Confidence Calibration of Reasoning LLMs

    Apr 21, 2026Thomas Zollo, Jimmy Wang, Richard ZemelConfidence Estimation in Language ModelsLanguage Model Calibration

    Columbia University

  6. Beyond "I Don't Know": Evaluating LLM Self-Awareness in Discriminating Data and Model Uncertainty

    Apr 19, 2026Jingyi Ren, Ante Wang, Yunghwei Lai +5LLM EvaluationSelective Prediction

    Dept. of Comp. Sci. & Tech., Institute for AI, Tsinghua University, Beijing, China · Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China

  7. Instinct vs. Reflection: Unifying Token and Verbalized Confidence in Multimodal Large Models

    Apr 19, 2026Yunkai Dang, Yifan Jiang, Yizhu Jiang +3Selective PredictionConfidence Estimation in Language Models

    School of Artificial Intelligence, Nanjing University.

  8. Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantification

    Apr 18, 2026Kimia Hamidieh, Veronika Thost, Walter Gerych +2Selective PredictionConfidence Estimation in Language Models

    1MIT · MIT-IBM Watson AI Lab · 3WPI +1

  9. Beyond Surface Statistics: Robust Conformal Prediction for LLMs via Internal Representations

    Apr 17, 2026Yanli Wang, Peng Kuang, Xiaoyu Han +2Language Model RobustnessConformal Prediction

    Imperial College London · Zhejiang University · University of Illinois Urbana-Champaign +1

  10. Calibrated Selective Fact-Checking via Evidence Chain Evaluation

    Apr 15, 2026Dekun YangAutomated Fact-CheckingSelective Prediction

    Zhejiang University

  11. Enhancing Confidence Estimation in Telco LLMs via Twin-Pass CoT-Ensembling

    Apr 14, 2026Anton Saenko, Pranshav Gajjar, Abiodun Ganiyu +1Confidence Estimation in Language ModelsLanguage Model Calibration

    NextG Wireless Lab, North Carolina State University, Raleigh, NC, USA

  12. Agentic Control in Variational Language Models

    Apr 14, 2026Yves RuffenachLanguage Model-Based ControlLanguage Modeling

    Conservatoire National des Arts et Métiers, Strasbourg, France

  13. Calibrated Confidence Estimation for Tabular Question Answering

    Apr 14, 2026Lukas VossConfidence Estimation in Language ModelsLanguage Model Calibration

    Independent Researcher

  14. Masked by Consensus: Disentangling Privileged Knowledge in LLM Correctness

    Apr 14, 2026Tomer Ashuach, Shai Gretz, Yoav Katz +2Language Model IntrospectionLanguage Model Self-Assessment

    Technion – Israel Institute of Technology · IBM Research · Kempner Institute, Harvard University

  15. Confidence under Visual Token Pruning: Removed Evidence and Risk-Controlled Token Budgets for MLLMs

    Apr 13, 2026Kaizhen Tan, Yang Feng, Heqing Du +3VLM EvaluationConfidence Estimation for VLMs

    Carnegie Mellon University, Pittsburgh, PA, USA · Columbia University, New York, NY, USA

  16. CLSGen: A Dual-Head Fine-Tuning Framework for Joint Probabilistic Classification and Verbalized Explanation

    Apr 13, 2026WonJin Yoon, Kangyu Zhu, Ian Bulovic +5LLM Fine-TuningConfidence Estimation in Language Models

    Boston Children’s Hospital · Harvard Medical School · University of Colorado Anschutz Medical Campus +2

  17. Quantisation Reshapes the Metacognitive Geometry of Language Models

    Apr 10, 2026Jon-Paul CacioliLanguage Model Self-AssessmentMetacognition in Language Models

    Independent Researcher, Melbourne, Australia

  18. Confident in a Confidence Score: Investigating the Sensitivity of Confidence Scores to Supervised Fine-Tuning

    Apr 10, 2026Lorenzo Jaime Yu Flores, Cesare Spinoso Di-Piano, Jackie Chi Kit CheungConfidence Estimation in Language ModelsLanguage Model Calibration

    Mila - Quebec AI Institute · McGill University · Canada CIFAR AI Chair, Mila

  19. Less Data Approximates More: Earning Faithful Confidence in High-Stakes Domains

    Apr 9, 2026Haokai Ma, Lee Yan Zhen, Gang Yang +4RL for Language ModelsReinforcement Learning

    National University of Singapore, Singapore · Singapore Management University, Singapore

  20. When Should a Language Model Trust Itself? Same-Model Self-Verification as a Conditional Confidence Signal

    Apr 8, 2026Aditya Ajay PhalodLanguage Model Self-VerificationLanguage Model Self-Assessment

    Independent Researcher

  21. Fine-grained Approaches for Confidence Calibration of LLMs in Automated Code Revision

    Apr 8, 2026Hong Yi Lin, Chunhua Liu, Haoyu Gao +2Confidence Estimation in Language ModelsLanguage Model Calibration

  22. SELFDOUBT: Uncertainty Quantification for Reasoning LLMs via the Hedge-to-Verify Ratio

    Apr 7, 2026Satwik Pandey, Suresh Raghu, Shashwat PandeyLLM Uncertainty EstimationConfidence Estimation in Language Models

    Independent Researcher · Zillow Group

  23. Towards Trustworthy Report Generation: A Deep Research Agent with Progressive Confidence Estimation and Calibration

    Apr 7, 2026Yi Yuan, Xuhong Wang, Shanzhe LeiDeep Research AgentsTrust in AI

    Shanghai Artificial Intelligence Laboratory · Southeast University

  24. Identifying Influential N-grams in Confidence Calibration via Regression Analysis

    Apr 7, 2026Shintaro Ozaki, Wataru Hashimoto, Hidetaka Kamigaito +2Language Model CalibrationConfidence Estimation in Language Models

    Nara Institute of Science and Technology (NAIST) · The University of Tokyo

  25. Confidence Should Be Calibrated More Than One Turn Deep

    Apr 7, 2026Zhaohan Zhang, Chengzhengxu Li, Xiaoming Liu +3Confidence Estimation in Language ModelsLanguage Model Calibration

    Queen Mary University of London · Xi’an Jiaotong University

  26. Early Stopping for Large Reasoning Models via Confidence Dynamics

    Apr 6, 2026Parsa Hosseini, Sumit Nawathe, Mahdi Salmani +2Early Stopping for Language Model ReasoningEarly Stopping

    University of Maryland · University of Southern California

  27. I-CALM: Incentivizing Confidence-Aware Abstention for LLM Selective Answering

    Apr 5, 2026Haotian Zong, Binze Li, Yufei Long +3Selective PredictionLLM Hallucination Mitigation

    Department of Applied Mathematics and Statistics, Johns Hopkins University, Baltimore, MD 21218, USA · Department of Computer Science, Johns Hopkins University, Baltimore, MD 21218, USA · School of Government and Policy, Johns Hopkins University, Washington, D.C. 20001, USA +1

  28. Entropy and Attention Dynamics in Small Language Models: A Trace-Level Structural Analysis on the TruthfulQA Benchmark

    Apr 4, 2026Adeyemi Adeseye, Aisvarya Adeseye, Hannu Tenhunen +1Small Language ModelsLLM Honesty

    Brilloconnetz Partners avoin yhtiö, Turku, Finland · University of Turku, Turku, Finland · Royal Institute of Technology, Stockholm, Sweden

  29. Confidence Calibration in Large Language Models

    Apr 3, 2026Noam Michael, Daniel BenShushan, Jacob Bien +1Language Model CalibrationConfidence Estimation in Language Models

    U.C. Berkeley · University of Southern California

  30. BAS: A Decision-Theoretic Approach to Evaluating Large Language Model Confidence

    Apr 3, 2026Sean Wu, Fredrik K. Gustafsson, Edward Phillips +3LLM EvaluationConfidence Estimation in Language Models

    Department of Engineering Science, University of Oxford · Oxford Suzhou Centre for Advanced Research