Language Model Calibration

Follow this topic Ask about this topic

Language model calibration asks whether a model’s stated or computed confidence corresponds to how often its answers are correct, so systems can decide when to answer, retrieve evidence, defer, or abstain. Researchers estimate confidence from verbal reports, token probabilities, self-consistency, or hidden representations, then improve it with post-hoc methods such as temperature scaling and isotonic regression, conformal prediction, or training methods including supervised fine-tuning and reinforcement learning. Evaluations commonly use question answering and mathematical reasoning benchmarks, and increasingly test retrieval routing, model judges, medical tasks, and performance under domain or prompt shifts. A central tension is that calibration can change with the elicitation protocol and deployment context, and well-calibrated probabilities do not necessarily rank errors well or guarantee safe decisions.

Latest papers

386 papers67 papers in the last four weeks, up 40% on the four weeks before. 0.4% of all new papers.

Less Data Approximates More: Earning Faithful Confidence in High-Stakes Domains
Apr 9, 2026Haokai Ma, Lee Yan Zhen, Gang Yang +4RL for Language Models Reinforcement Learning
National University of Singapore, Singapore · Singapore Management University, Singapore
Rethinking Residual Errors in Compensation-based LLM Quantization
Apr 9, 2026Shuaiting Li, Juncan Deng, Kedong Xu +5Quantization Error Compensation LLM Quantization
Zhejiang University · vivo Mobile Communication Co., Ltd
SYN-DIGITS: A Synthetic Control Framework for Calibrated Digital Twin Simulation
Apr 8, 2026Grace Jiarui Fan, Chengpiao Huang, Tianyi Peng +2Synthetic Control Language Model Calibration
Finance Division, Columbia Business School. · Department of IEOR, Columbia University · Decision, Risk, and Operations Division, Columbia Business School. +1
Improving Semantic Uncertainty Quantification in Language Model Question-Answering via Token-Level Temperature Scaling
Apr 8, 2026Tom A. Lamb, Desi R. Ivanova, Philip H. S. Torr +1Language Model Calibration LLM Uncertainty Estimation
University of Oxford · University of Toronto & Vijil
Persona Matters: Effects of Activation Steering on Short Answer Generation and Scoring
Apr 8, 2026Yongchao Wu, Aron HenrikssonOpen-Ended Generation Language Model Steering
Stockholm University, NOD-huset, Borgarfjordsgatan 12, 16455 Stockholm, Sweden
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 Models Language Model Calibration
Identifying Influential N-grams in Confidence Calibration via Regression Analysis
Apr 7, 2026Shintaro Ozaki, Wataru Hashimoto, Hidetaka Kamigaito +2Language Model Calibration Confidence Estimation in Language Models
Nara Institute of Science and Technology (NAIST) · The University of Tokyo
Same Graph, Different Likelihoods: Calibration of Autoregressive Graph Generators via Permutation-Equivalent Encodings
Apr 7, 2026Laurits Fredsgaard, Aaron Thomas, Michael Riis Andersen +2Autoregressive Generation Permutation-Invariant Learning
Technical University of Denmark · University of Birmingham · National Institute of Informatics
Confidence Should Be Calibrated More Than One Turn Deep
Apr 7, 2026Zhaohan Zhang, Chengzhengxu Li, Xiaoming Liu +3Confidence Estimation in Language Models Language Model Calibration
Queen Mary University of London · Xi’an Jiaotong University
From Exposure to Internalization: Dual-Stream Calibration for In-context Clinical Reasoning
Apr 7, 2026Chuang Zhao, Hongke Zhao, Xiaofang Zhou +1Clinical Reasoning Adaptive Inference
Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong, SAR, China · College of Management and Economics, Laboratory of Computation and Analytics of Complex Management Systems (CACMS), Tianjin University, Tianjin 30072, China · Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, SAR, China
Confidence Calibration in Large Language Models
Apr 3, 2026Noam Michael, Daniel BenShushan, Jacob Bien +1Language Model Calibration Confidence Estimation in Language Models
U.C. Berkeley · University of Southern California
BAS: A Decision-Theoretic Approach to Evaluating Large Language Model Confidence
Apr 3, 2026Sean Wu, Fredrik K. Gustafsson, Edward Phillips +3LLM Evaluation Confidence Estimation in Language Models
Department of Engineering Science, University of Oxford · Oxford Suzhou Centre for Advanced Research
Overconfidence and Calibration in Medical VQA: Empirical Findings and Hallucination-Aware Mitigation
Apr 2, 2026Ji Young Byun, Young-Jin Park, Jean-Philippe Corbeil +1Vision-Language Models VLM Hallucination
Johns Hopkins University, School of Medicine · Massachusetts Institute of Technology · Microsoft Healthcare & Life Sciences
Social Meaning in Large Language Models: Structure, Magnitude, and Pragmatic Prompting
Apr 2, 2026Roland MühlenberndPragmatic Reasoning in Language Models Language Model Calibration
Leibniz-Centre General Linguistics, Berlin, Germany
Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs
Apr 1, 2026Tianyi Zhao, Yinhan He, Wendy Zheng +2Confidence Estimation in Language Models Language Model Calibration
University of Virginia
Online Reasoning Calibration: Test-Time Training Enables Generalizable Conformal LLM Reasoning
Apr 1, 2026Cai Zhou, Zekai Wang, Menghua Wu +6Conformal Prediction for Language Models Language Model Calibration
Department of Electrical Engineering and Computer Science (MIT EECS) · Computer Science and Artificial Intelligence Laboratory (MIT CSAIL) · Laboratory for Information and Decision Systems (MIT LIDS) +1
Towards Reliable Truth-Aligned Uncertainty Estimation in Large Language Models
Apr 1, 2026Ponhvoan Srey, Quang Minh Nguyen, Xiaobao Wu +1LLM Uncertainty Estimation Uncertainty Calibration
Nanyang Technological University, Singapore · KAIST, South Korea · Shanghai Jiao Tong University
Act or Escalate? Evaluating Escalation Behavior in Automation with Language Models
Mar 31, 2026Matthew DosSantos DiSorbo, Harang JuLLM Decision-Making AI-Assisted Decision Making
Harvard Business School · Johns Hopkins Carey Business School
When Can We Trust LLM Graders? Calibrating Confidence for Automated Assessment
Mar 31, 2026Robinson Ferrer, Damla Turgut, Zhongzhou Chen +1Confidence Estimation in Language Models Language Model Calibration
University of Central Florida
Do LLMs Know What They Know? Measuring Metacognitive Efficiency with Signal Detection Theory
Mar 26, 2026Jon-Paul CacioliConfidence Estimation in Language Models Language Model Calibration
Independent Researcher, Melbourne, Australia
Closing the Confidence-Faithfulness Gap in Large Language Models
Mar 26, 2026Miranda Muqing Miao, Lyle UngarConfidence Estimation in Language Models Verbalized Confidence Estimation
University of Pennsylvania · Department of Computer and Information Science
Set-Valued Prediction for Large Language Models with Feasibility-Aware Coverage Guarantees
Mar 24, 2026Ye Li, Anqi Hu, Yuanchang Ye +3Set-Valued Prediction LLM Uncertainty Estimation
University of Electronic Science and Technology of China, Chengdu, Sichuan, China · Zhejiang University of Finance and Economics, Hangzhou, Zhejiang, China · Southeast University, Nanjing, Jiangsu, China
Entropy Alone is Insufficient for Safe Selective Prediction in LLMs
Mar 22, 2026Edward Phillips, Fredrik K. Gustafsson, Sean Wu +2Selective Prediction LLM Uncertainty Estimation
Department of Engineering Science, University of Oxford · Oxford Suzhou Centre for Advanced Research, University of Oxford, Suzhou
DiscoUQ: Structured Disagreement Analysis for Uncertainty Quantification in LLM Agent Ensembles
Mar 21, 2026Bo JiangUncertainty Quantification LLM Uncertainty Estimation
Temple University
Self-Calibrating Language Models via Test-Time Discriminative Distillation
Mar 18, 2026Mohamed Rissal Hedna, Jan Strich, Martin Semmann +1Inference-Time Adaptation of Language Models Language Model Calibration
Hub of Computing and Data Science (HCDS), University of Hamburg, Germany
Noise-Response Calibration: A Causal Intervention Protocol for LLM-Judges
Mar 17, 2026Maxim Khomiakov, Jes FrellsenLanguage Model Calibration LLM-as-a-Judge
Technical University of Denmark, Kgs. Lyngby, Denmark · Normal Computing Corporation, New York, NY, USA · Pioneer Centre for Artificial Intelligence, Copenhagen, Denmark
LLMs as Signal Detectors: Sensitivity, Bias, and the Temperature-Criterion Analogy
Mar 16, 2026Jon-Paul CacioliLLM Evaluation Language Model Calibration
Independent Researcher, Melbourne, Australia
CHiL(L)Grader: Calibrated Human-in-the-Loop Short-Answer Grading
Mar 12, 2026Pranav Raikote, Korbinian Randl, Ioanna Miliou +2Automated Grading AI in Education
Department of Computer and Systems Sciences, Stockholm University, 164 25 Kista, Sweden
Beyond 0-100: How Confidence Scale Design Shapes Verbalized Confidence and LLM Metacognition
Mar 10, 2026Yuyang Dai, Yuxia WangConfidence Estimation in Language Models Language Model Calibration
INSAIT
Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards
Mar 10, 2026Zhengzhao Ma, Xueru Wen, Boxi Cao +6Reinforcement Learning RL for Language Model Reasoning
Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China · Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China +2

Apr 9, 2026J/K move · Enter open · S save

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

Haokai Ma, Lee Yan Zhen, Gang Yang, Yunxiang Chen+3

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

RL for Language Models Reinforcement Learning Reasoning Distillation Confidence Estimation in Language Models LLM Fine-Tuning Language Model Calibration

Open paper AskPDF arXiv

Large language models are increasingly deployed in high-stakes domains, where confident yet incorrect inferences may cause severe real-world harm, bringing the long-overlooked issue of confidence faithfulness to the forefront. A promising solution jointly optimizes unsupervised Reinforcement Learning from Internal Feedback (RLIF) with reasoning-trace-guided Reasoning Distillation (RD), yet it faces three persistent challenges, namely the scarcity of high-quality training corpora, factually unwarranted overconfidence, and erroneous updates amplified by indiscriminate fusion. Inspired by how human confidence accumulates from uncertainty to certainty, we propose Progressive Reasoning Gain (PRG) to measure whether reasoning steps progressively strengthen confidence in the final answer. Building on PRG, we introduce HyTuning, a hybrid post-training framework that adaptively reweights RD and RLIF, using scarce supervised reasoning traces as a stable anchor while exploiting abundant unlabeled queries for scalability. Experiments on several domain-specific and general benchmarks demonstrate that HyTuning improves accuracy while achieving confidence faithfulness under limited supervision, supporting a practical ``Less Data Approximates More'' effect. Our code will be released upon acceptance.