LLM Uncertainty Estimation

LLM: Large Language Model

Large language model uncertainty estimation studies how to tell when an answer, reasoning step, or action may be unreliable, and whether the cause is missing knowledge, ambiguous input, or random variation. Methods include sampling and semantic agreement, token probabilities and entropy, confidence calibration, probes of hidden representations, and Bayesian or evidential models; conformal prediction adds statistical guarantees for abstention or prediction sets. These signals are used to decide when to answer, ask for clarification, retrieve evidence, spend more computation, or defer to a person, with tests spanning factual QA, reasoning, medicine, code, and multimodal tasks. A central challenge is that no signal works reliably across settings: confidence can be miscalibrated or reflect commitment rather than correctness, and agreement may preserve shared errors, so methods need task-specific validation and robust evaluation under ambiguity and distribution shift.

Latest papers

403 papers38 papers in the last four weeks, up 9% on the four weeks before. 0.2% of all new papers.

Sample Transform Cost-Based Training-Free Hallucination Detector for Large Language Models
Mar 17, 2026Zeyang Ding, Xinglin Hu, Jicong FanLLM Hallucination Detection LLM Reliability
The Chinese University of Hong Kong, Shenzhen
DynHD: Hallucination Detection for Diffusion Large Language Models via Denoising Dynamics Deviation Learning
Mar 17, 2026Yanyu Qian, Yue Tan, Yixin Liu +2Hallucination Detection Diffusion Language Models
Nanyang Technological University, Singapore · Griffith University, Australia
Between the Layers Lies the Truth: Uncertainty Estimation in LLMs Using Intra-Layer Local Information Scores
Mar 17, 2026Zvi N. Badash, Yonatan Belinkov, Moti FreimanUncertainty Quantification LLM Uncertainty Estimation
Faculty of Data and Decision Sciences, Technion — Israel Institute of Technology, Haifa, Israel · Faculty of Computer Science, Technion — Israel Institute of Technology, Haifa, Israel · Faculty of Biomedical Engineering, Technion — Israel Institute of Technology, Haifa, Israel
Verbalizing LLM's Higher-order Uncertainty via Imprecise Probabilities
Mar 11, 2026Anita Yang, Krikamol Muandet, Michele Caprio +2Imprecise Probability LLM Uncertainty Estimation
Lattice Lab, Toyota Motor Corporation, Japan · Department of Computer Science, University of Tokyo, Japan · Rational Intelligence Lab, CISPA, Helmholtz Center for Information Security, Germany +3
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
From Scalars to Tensors: Declared Losses Recover Epistemic Distinctions That Neutrosophic Scalars Cannot Express
Mar 10, 2026Tony MasonEpistemic Uncertainty LLM Evaluation
University of British Columbia, Vancouver, Canada · Georgia Institute of Technology, Atlanta, USA
Learning When to Sample: Confidence-Aware Selective Sampling for Efficient Chain-of-Thought Reasoning
Mar 9, 2026Juming Xiong, Kevin Guo, Congning Ni +7CoT Reasoning Efficient Language Model Reasoning
1Vanderbilt University · 2Vanderbilt University Medical Center · 3Intuit AI Research
TableMind++: An Uncertainty-Aware Programmatic Agent for Tool-Augmented Table Reasoning
Mar 8, 2026Mingyue Cheng, Shuo Yu, Chuang Jiang +5LLM Reasoning Memory-Augmented Language Model Agents
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China
From Entropy to Calibrated Uncertainty: Training Language Models to Reason About Uncertainty
Mar 6, 2026Azza Jenane, Nassim Walha, Lukas Kuhn +1LLM Uncertainty Estimation Language Model Calibration
German Cancer Research Center (DKFZ) German Cancer Consortium (DKTK) Goethe University Frankfurt, Germany
InfoGatherer: Principled Information Seeking via Evidence Retrieval and Strategic Questioning
Mar 6, 2026Maksym Taranukhin, Shuyue Stella Li, Evangelos Milios +3Document QA LLM Decision-Making
University of British Columbia · Vector Institute · University of Washington +2
Confidence Before Answering: A Paradigm Shift for Efficient LLM Uncertainty Estimation
Mar 6, 2026Changcheng Li, Jiancan Wu, Hengheng Zhang +5Confidence Estimation in Language Models LLM Uncertainty Estimation
University of Science and Technology of China · Huawei Inc.
Can LLMs Capture Expert Uncertainty? A Comparative Analysis of Value Alignment in Ethnographic Qualitative Research
Mar 5, 2026Arina Kostina, Marios Dikaiakos, Alejandro Porcel +1LLM Evaluation LLM Uncertainty Estimation
University of Cyprus, Cyprus · Trinetra Investment Management LLP, UK · University of Cambridge, UK
Eliciting Numerical Predictive Distributions of LLMs Without Autoregression
Mar 3, 2026Julianna Piskorz, Katarzyna Kobalczyk, Mihaela van der SchaarLLM Uncertainty Estimation LLM Inference
Department of Applied Mathematics and Theoretical Physics, University of Cambridge
DenoiseFlow: Uncertainty-Aware Denoising for Reliable LLM Agentic Workflows
Feb 28, 2026Yandong Yan, Junwei Peng, Shijie Li +7LLM Agent Reliability LLM Agent Workflow Optimization
School of Computer Science, Peking University · School of Electronics Engineering and Computer Science, Peking University · China Southern Power Grid +6
Uncertainty Quantification for Multimodal Large Language Models with Incoherence-adjusted Semantic Volume
Feb 27, 2026Gregory Kang Ruey Lau, Hieu Dao, Nicole Kan Hui Lin +1LLM Uncertainty Estimation Multimodal Large Language Models
Department of Computer Science, National University of Singapore
Uncertainty-aware Language Guidance for Concept Bottleneck Models
Feb 26, 2026Yangyi Li, Mengdi HuaiConcept Bottleneck Models LLM Uncertainty Estimation
Iowa State University, Ames IA 50011, USA
Black-Box Reliability Certification for AI Agents via Self-Consistency Sampling and Conformal Calibration
Feb 24, 2026Charafeddine MouzouniAI Agent Reliability Trustworthy AI
OPIT – Open Institute of Technology, and Cohorte AI, Paris, France.
Real-Time Trustworthiness Scoring for LLM Structured Outputs and Data Extraction
Feb 24, 2026Hui Wen Goh, Jonas MuellerLLM Answer Verification LLM Uncertainty Estimation
Cleanlab
How Confident Is the First Token? An Uncertainty-Calibrated Prompt Optimization Framework for Large Language Model Classification and Understanding
Feb 23, 2026Wei Chen, Guoyang Ju, Yuanyuan QiLLM Input Optimization LLM Prompting
China Jiliang University, Hangzhou, China
Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study
Feb 19, 2026Dylan Bouchard, Mohit Singh Chauhan, Viren Bajaj +1LLM Hallucination Mitigation Hallucination in Language Models
CVS Health, Wellesley, MA
LLMs Exhibit Significantly Lower Uncertainty in Creative Writing Than Professional Writers
Feb 18, 2026Peiqi SuiText Generation Computational Creativity
Department of English, McGill University
How Uncertain Is the Grade? A Benchmark of Uncertainty Metrics for LLM-Based Automatic Assessment
Feb 17, 2026Hang Li, Kaiqi Yang, Xianxuan Long +9Uncertainty Quantification LLM Uncertainty Estimation
Washington State University, Pullman, USA
The Well-Tempered Classifier: Some Elementary Properties of Temperature Scaling
Feb 16, 2026Pierre-Alexandre Mattei, Bruno LoureiroModel Calibration LLM Uncertainty Estimation
Université Côte d’Azur, Inria, CNRS, LJAD, France · Département d’Informatique, École Normale Supérieure - PSL, CNRS, France
On Calibration of Large Language Models: From Response To Capability
Feb 14, 2026Sin-Han Yang, Cheng-Kuang Wu, Chieh-Yen Lin +3LLM Evaluation Confidence Estimation in Language Models
Appier AI Research · National Taiwan University
When Agents Disagree With Themselves: Behavioral Consistency as an Uncertainty Signal for LLM Agents
Feb 12, 2026Aman MehtaAI Agent Reliability Selective Prediction
Snowflake AI Research
Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know"
Feb 4, 2026Dhruv Madhwal, Lyuxin David Zhang, Dan Roth +2LLM Prompting Question Decomposition
Arizona State University · University of Pennsylvania · Oracle AI
Semantic Self-Distillation for Language Model Uncertainty
Feb 4, 2026Edward Phillips, Sean Wu, Fredrik K. Gustafsson +2Uncertainty Quantification Confidence Estimation in Language Models
Department of Engineering Science, University of Oxford · Oxford Suzhou Centre for Advanced Research, University of Oxford, Suzhou
Uncertainty Localization in LLM Reasoning via Embedding Perturbations
Feb 2, 2026Qihao Wen, Jiahao Wang, Yang Nan +3LLM Reliability LLM Uncertainty Estimation
University of Arizona · Michigan State University
Towards Reliable Medical LLMs: Benchmarking and Enhancing Confidence Estimation of Large Language Models in Medical Consultation
Jan 22, 2026Zhiyao Ren, Yibing Zhan, Siyuan Liang +3Healthcare Clinical Reasoning
Nanyang Technological University, Singapore, Singapore. · Wuhan University, Wuhan, China.
Calibration Is Not Enough: Evaluating Confidence Estimation Under Language Variations
Jan 12, 2026Yuxi Xia, Dennis Ulmer, Terra Blevins +3LLM Uncertainty Estimation Confidence Estimation in Language Models
Faculty of Computer Science, UniVie Doctoral School Computer Science · Faculty of Philological and Cultural Studies, University of Vienna, Austria · ILLC, University of Amsterdam, Netherlands +2

Mar 17, 2026J/K move · Enter open · S save

Sample Transform Cost-Based Training-Free Hallucination Detector for Large Language Models

Zeyang Ding, Xinglin Hu, Jicong Fan

The Chinese University of Hong Kong, Shenzhen

LLM Hallucination Detection LLM Reliability LLM Uncertainty Estimation

Open paper AskPDF arXiv

Hallucinations in large language models (LLMs) remain a central obstacle to trustworthy deployment, motivating detectors that are accurate, lightweight, and broadly applicable. Since an LLM with a prompt defines a conditional distribution, we argue that the complexity of the distribution is an indicator of hallucination. However, the density of the distribution is unknown and the samples (i.e., responses generated for the prompt) are discrete distributions, which leads to a significant challenge in quantifying the complexity of the distribution. We propose to compute the optimal-transport distances between the sets of token embeddings of pairwise samples, which yields a Wasserstein distance matrix measuring the costs of transforming between the samples. This Wasserstein distance matrix provides a means to quantify the complexity of the distribution defined by the LLM with the prompt. Based on the Wasserstein distance matrix, we derive two complementary signals: AvgWD, measuring the average cost, and EigenWD, measuring the cost complexity. This leads to a training-free detector for hallucinations in LLMs. We further extend the framework to black-box LLMs via teacher forcing with an accessible teacher model. Experiments show that AvgWD and EigenWD are competitive with strong uncertainty baselines and provide complementary behavior across models and datasets, highlighting distribution complexity as an effective signal for LLM truthfulness.