Confidence Estimation in Language Models

Follow this topic Ask about this topic

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

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

Same Answer, Different Confidence: Protocol Sensitivity in LLM Confidence Calibration
May 26, 2026Hankyeol Kim, Pilsung KangLLM Evaluation Confidence Estimation in Language Models
Seoul National University
Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals
May 25, 2026Federico Torrielli, Peter Schneider-Kamp, Lukas Galke PoechConfidence Estimation in Language Models LLM Interpretability
University of Turin · University of Southern Denmark
Second Guess: Detecting Uncertainty Through Abstention and Answer Stability in Small Language Models
May 25, 2026Ashwath Vaithinathan Aravindan, Mayank KejriwalConfidence Estimation in Language Models Multiple-Choice Question Answering
University of Southern California Los Angeles, 90007, California, United States of America · Information Sciences Institute 4676 Admiralty Way #1001, Los Angeles, 90292, California, United States of America
Decision-Making with Lightweight Confidence-Aware Language Model for Autonomous Driving
May 25, 2026Ruoyu Yao, Ruiguo Zhong, Pei Liu +3Confidence Estimation in Language Models Language Model Distillation
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511453, China
Inference Time Optimization with Confidence Dynamics
May 24, 2026Yu Wang, Minghao Liu, Jiayun Wang +3Inference-Time Optimization Confidence Estimation in Language Models
Center for Advanced AI, Accenture.
Trust but Verify: Prover-Verifier Deliberation for Selective LLM Prediction
May 24, 2026João Sedoc, Baotong Zhang, Dean FosterLLM Answer Verification Selective Prediction
New York University
Understanding and Mitigating Premature Confidence for Better LLM Reasoning
May 23, 2026Jingchu Gai, Guanning Zeng, Christina Baek +4Confidence Estimation in Language Models RL for Language Model Reasoning
1Carnegie Mellon University · 2Tsinghua University
LLMs Show No Signs Of Individuated Metacognition
May 22, 2026M. Moran, Mark WhitingLLM Evaluation Confidence Estimation in Language Models
Pareto AI
Calibration vs Decision Making: Revisiting the Reliability Paradox in Unlearned Language Models
May 20, 2026Divyaksh Shukla, Ashutosh ModiShortcut Learning in Language Models Confidence Estimation in Language Models
Indian Institute of Technology Kanpur (IIT Kanpur)
Reading Calibrated Uncertainty from Language Model Trajectories
May 19, 2026Aliai Eusebi, Alexander Herzog, Xiaoyu Liang +3Confidence Estimation in Language Models LLM Reliability
University College London, London, United Kingdom · Core46, London, United Kingdom
Retrieval-Augmented Linguistic Calibration
May 19, 2026Yi-Fan Yeh, Linwei Tao, Minjing Dong +4Confidence Estimation in Language Models Faithfulness of Language Model Reasoning
School of Computer Science University of Sydney Sydney, Australia · City University of Hong Kong Hong Kong · Shanghai Jiao Tong University Shanghai, China +1
Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution
May 19, 2026Xiaoou Liu, Tiejin Chen, Dengjia Zhang +3Uncertainty Quantification Confidence Estimation in Language Models
1Arizona State University · 2Johns Hopkins University · 3Purdue +1
Position: Uncertainty Quantification in LLMs is Just Unsupervised Clustering
May 19, 2026Tiejin Chen, Longchao Da, Xiaoou Liu +1LLM Evaluation Uncertainty Quantification
School of Computing and Augmented Intelligence, Arizona State University
Confidence Geometry Reveals Trace-Level Correctness in Large Language Model Reasoning
May 16, 2026Shuo Liu, Ding Liu, Shi-Ju RanConfidence Estimation in Language Models LLM Reliability
School of Computer Science and Technology, Tiangong University, Tianjin, China. · Center for Quantum Physics and Intelligent Sciences, Department of Physics, Capital Normal University, Beijing, China.
Margin-Adaptive Confidence Ranking for Reliable LLM Judgement
May 14, 2026Gaojie Jin, Yong Tao, Lijia Yu +1LLM Evaluation LLM-as-a-Judge
Department of Computer Science, University of Exeter · Institute of AI for Industries, Chinese Academy of Sciences · Department of Mathematics and Computer Science, Eindhoven University of Technology
Inducing Artificial Uncertainty in Language Models
May 13, 2026Sophia Hager, Simon Zeng, Nicholas AndrewsConfidence Estimation in Language Models Language Model Calibration
Johns Hopkins University · Microsoft
LLMs as Implicit Imputers: Uncertainty Should Scale with Missing Information
May 13, 2026Stef van BuurenLLM Evaluation Confidence Estimation in Language Models
1. TNO - Netherlands Organization for Applied Scientific Research, Leiden · 2. Dept. of Methodology and Statistics, University of Utrecht
ORCE: Order-Aware Alignment of Verbalized Confidence in Large Language Models
May 12, 2026Chen Li, Xiaoling Hu, Songzhu Zheng +2Confidence Estimation in Language Models Language Model Calibration
Stony Brook University, NY, USA · Massachusetts General Hospital and Harvard Medical School, MA, USA · Morgan Stanley, NY, USA
Confidently Deceptive: On the Relationship Between Confidence and Deception in LLMs
May 12, 2026Ali Asad, Stephen Obadinma, Anshul Pattoo +2Language Model Safety Evaluation Confidence Estimation in Language Models
Department of Electrical and Computer Engineering & Ingenuity Labs Research Institute Queen’s University, Kingston, Canada
VERDI: Single-Call Confidence Estimation for Verification-Based LLM Judges via Decomposed Inference
May 11, 2026Jasmine Qi, Danylo Dantsev, Muyang SunPost-Hoc Calibration LLM-as-a-Judge
Indeed Inc.
Grounded or Guessing? LVLM Confidence Estimation via Blind-Image Contrastive Ranking
May 11, 2026Reza Khanmohammadi, Erfan Miahi, Simerjot Kaur +4VLM Evaluation Confidence Estimation for VLMs
Michigan State University · Independent AI Researcher · JPMorgan AI Research +1
A Semantic-Sampling Framework for Evaluating Calibration in Open-Ended Question Answering
May 8, 2026Zhanliang Wang, Jiancong Xiao, Ruochen Jin +3LLM Evaluation Confidence Estimation in Language Models
University of Pennsylvania, Philadelphia, PA · Dartmouth College, Hanover, NH
Beyond Confidence: Rethinking Self-Assessments for Performance Prediction in LLMs
May 8, 2026Sree Bhattacharyya, Samarth Khanna, Leona Chen +3LLM Evaluation Confidence Estimation in Language Models
Department of Informatics and Intelligent Systems, College of Information Sciences, The Pennsylvania State University. · Department of Computer Science and Engineering, College of Engineering, The Pennsylvania State University.
Measuring Black-Box Confidence via Reasoning Trajectories: Geometry, Coverage, and Verbalization
May 7, 2026Marc Boubnovski Martell, Josefa Lia Stoisser, Kaspar Märtens +4LLM Uncertainty Estimation CoT Reasoning
1Novo Nordisk · University of Oxford
Towards Generation-Efficient Uncertainty Estimation in Large Language Models
May 7, 2026Mingcheng Zhu, Yu Liu, Tingting ZhuLLM Inference Efficiency Uncertainty Quantification
University of Oxford
HyperLens: Quantifying Cognitive Effort in LLMs with Fine-grained Confidence Trajectory
May 7, 2026Chengda Lu, Xiaoyu Fan, Wei XuConfidence Estimation in Language Models LLM Interpretability
1IIIS, Tsinghua University · 2Shanghai Qi Zhi Institute.
Detecting Hallucinations in Large Language Models via Internal Attention Divergence Signals
May 6, 2026Gijs van DijkLanguage Model Error Detection Confidence Estimation in Language Models
Utrecht University
Zero-Shot Confidence Estimation for Small LLMs: When Supervised Baselines Aren't Worth Training
May 4, 2026Luong N. NguyenConfidence Estimation in Language Models Language Model Self-Assessment
Geometry-Calibrated Conformal Abstention for Language Models
Apr 30, 2026Rui Xu, Yi Chen, Sihong Xie +1Uncertainty Quantification Selective Prediction
Information Hub, AI Thrust Hong Kong University of Science and Technology (Guangzhou) Guangzhou, Guangdong, China
Distilling Self-Consistency into Verbal Confidence: A Pre-Registered Negative Result and Post-Hoc Rescue on Gemma 3 4B
Apr 27, 2026Jon-Paul CacioliSupervised Fine-Tuning Confidence Estimation in Language Models
Independent Researcher, Melbourne, Australia

May 26, 2026J/K move · Enter open · S save

Same Answer, Different Confidence: Protocol Sensitivity in LLM Confidence Calibration

Hankyeol Kim, Pilsung Kang

Seoul National University

LLM Evaluation Confidence Estimation in Language Models Language Model Calibration LLM Reliability LLM Uncertainty Estimation Verbalized Confidence Estimation

Open paper AskPDF arXiv

Large language models (LLM) can state their confidence in an answer (verbalized confidence), or the confidence can be read from the probability of the answer's tokens (token confidence). Comparisons of the two ask which is better calibrated, but the token probability of an answer depends on the text that precedes it. Across five open LLMs and four question-answering datasets, we fix each answer, its verbalized confidence, and its correctness label, and vary how each score is measured. The scores themselves change with the protocol, and so does the comparison between them. Changing the context in which the token probability is read shifts the gap between the two scores by about the size of the gap itself (.287 vs. .304 in expected calibration error, ECE; .189 vs. .145 in AUROC). The 95% interval of the shift excludes zero in 19 and 17 of the 20 settings, and under AUROC the shift has the same sign in all of them, so the context changes how answers are ranked. The better score flips in 8 settings under each metric, counting only flips that the intervals support, and the shift also appears in four larger models of up to 72B parameters. Most of the shift appears with changes to the instruction, not to the position of the answer. Other measurement choices also matter, and stated confidence depends on how a supplied answer is written. We turn these results into a reporting checklist for LLM confidence and its comparisons.