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.

Evolutionary Search for Automated Design of Uncertainty Quantification Methods
Apr 3, 2026Mikhail Seleznyov, Daniil Korbut, Viktor Moskvoretskii +3Uncertainty Quantification LLM Uncertainty Estimation
AIRI · Skoltech · Amazon +2
Scalable Variational Bayesian Fine-Tuning of LLMs via Orthogonalized Low-Rank Adapters
Apr 3, 2026Haotian Xiang, Bingcong Li, Qin LuLLM Uncertainty Estimation Bayesian LoRA
School of Electrical and Computer Engineering, University of Georgia, Athens, GA, USA · Department of Computer Science, ETH Zurich, Zurich, Switzerland
GRADE: Probing Knowledge Gaps in LLMs through Gradient Subspace Dynamics
Apr 3, 2026Yujing Wang, Yuanbang Liang, Yukun Lai +2LLM Interpretability LLM Uncertainty Estimation
Beihang University · Cardiff University · King’s College London
Bayesian Elicitation with LLMs: Model Size Helps, Extra "Reasoning" Doesn't Always
Apr 2, 2026Luka Hobor, Mario Brcic, Mihael Kovac +1Probability Elicitation from Language Models LLM Uncertainty Estimation
University of Zagreb Faculty of Electrical Engineering and Computing, Zagreb, Croatia
From Guessing to Placeholding: A Cost-Theoretic Framework for Uncertainty-Aware Code Completion
Apr 2, 2026Liang Zhu, Haolin Chen, Lidong Zhao +1Code Generation LLM Uncertainty Estimation
1Tencent, Shenzhen, China
Anchored Confabulation: Partial Evidence Non-Monotonically Amplifies Confident Hallucination in LLMs
Apr 2, 2026Ashish Balkishan LathkarHallucination in Language Models Confidence Estimation in Language Models
M.S. Data Science, Florida State University
Scheduling LLM Inference with Uncertainty-Aware Output Length Predictions
Apr 1, 2026Haoyu Zheng, Yongqiang Zhang, Fangcheng Fu +7LLM Inference Scheduling LLM Uncertainty Estimation
School of Computer Science, Wuhan University, Wuhan, China · Dameng Database Co., Ltd., Wuhan, China · School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China +2
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
Measuring (some aspects of) the metacognition of AI
Mar 31, 2026Richard Servajean, Philippe ServajeanLLM Evaluation LLM Uncertainty Estimation
Center for Brain Science, RIKEN, Saitama, Japan. · National Institute of Advanced Industrial Science and Technology (AIST), Tokyo, Japan. · Department of Psychology, Paul-Val´ery University, Montpellier, France.
An Isotropic Approach to Efficient Uncertainty Quantification with Gradient Norms
Mar 31, 2026Nils Grünefeld, Jes Frellsen, Christian HardmeierUncertainty Quantification LLM Uncertainty Estimation
1IT University of Copenhagen · 3Pioneer Centre for Artificial Intelligence · 2Technical University of Denmark
Internal Knowledge Without External Expression: Probing the Generalization Boundary of a Classical Chinese Language Model
Mar 31, 2026Jiuting Chen, Yuan Lian, Hao Wu +4Metacognition in Language Models Factual Knowledge in Language Models
Eaglewood Japan Co., Ltd.
Route-Induced Density and Stability (RIDE): Controlled Intervention and Mechanism Analysis of Routing-Style Meta Prompts on LLM Internal States
Mar 31, 2026Dianxing Zhang, Gang Li, Sheng LiLLM Routing LLM Interpretability
Digital China AI Research Institute
CoE: Collaborative Entropy for Uncertainty Quantification in Agentic Multi-LLM Systems
Mar 30, 2026Kangkang Sun, Jun Wu, Jianhua Li +3LLM Uncertainty Estimation Multi-LLM Collaboration
Shanghai Key Laboratory of Integrated Administration Technologies for Information Security School of Computer Science Shanghai Jiao Tong University Shanghai, China · School of Science and Engineering The Chinese University of Hong Kong, Shenzhen Shenzhen, China
Variational Neurons in Transformers for Language Modeling
Mar 30, 2026Yves RuffenachLLM Uncertainty Estimation Transformer
Conservatoire National des Arts et Métiers Strasbourg, France
A Formal Framework for Uncertainty Analysis of Text Generation with Large Language Models
Mar 27, 2026Steffen Herbold, Florian LemmerichLLM Uncertainty Estimation
Faculty of Computer Science and Mathematics, University of Passau, Passau, Germany
Generative Score Inference for Multimodal Data
Mar 27, 2026Xinyu Tian, Xiaotong ShenLLM Uncertainty Estimation Multimodal Learning
School of Statistics, University of Minnesota
Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents
Mar 27, 2026Nicholas Edwards, Sebastian SchusterMulti-Agent LLM Systems AI Coding Agents
Faculty of Computer Science, University of Vienna, Vienna, Austria · UniVie Doctoral School Computer Science, University of Vienna, Vienna, Austria
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
The Anatomy of Uncertainty in LLMs
Mar 26, 2026Aditya Taparia, Ransalu Senanayake, Kowshik Thopalli +1LLM Auditing LLM Reliability
School of Computing and Augmented Intelligence, Arizona State University · Lawrence Livermore National Laboratory
LogitScope: A Framework for Analyzing LLM Uncertainty Through Information Metrics
Mar 26, 2026Farhan Ahmed, Yuya Jeremy Ong, Chad DeLucaLLM Uncertainty Estimation Uncertainty Quantification
IBM Research · Plastic Labs
The Alignment Tax: Response Homogenization in Aligned LLMs and Its Implications for Uncertainty Estimation
Mar 25, 2026Mingyi LiuHomogenization in Language Models LLM Alignment
Independent Researcher
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
INTRYGUE: Induction-Aware Entropy Gating for Reliable RAG Uncertainty Estimation
Mar 23, 2026Alexandra Kuleshova, Andrei Volodichev, Daria Kotova +1Hallucination in RAG Hallucination Detection
Applied AI Institute
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
Semantic Token Clustering for Efficient Uncertainty Quantification in Large Language Models
Mar 20, 2026Qi Cao, Andrew Gambardella, Takeshi Kojima +2LLM Uncertainty Estimation LLM Reliability
The University of Tokyo, Japan
How Uncertainty Estimation Scales with Sampling in Reasoning Models
Mar 19, 2026Maksym Del, Markus Kängsepp, Marharyta Domnich +4LLM Uncertainty Estimation Uncertainty Quantification
Institute of Computer Science, University of Tartu
Entropy trajectory shape predicts LLM reasoning reliability: A diagnostic study of uncertainty dynamics in chain-of-thought
Mar 19, 2026Xinghao ZhaoLLM Uncertainty Estimation LLM Reliability
Huazhong University of Science and Technology
UT-ACA: Uncertainty-Triggered Adaptive Context Allocation for Long-Context Inference
Mar 19, 2026Lang Zhou, Shuxuan Li, Zhuohao Li +3Long-Context Inference LLM Context Management
School of Computer Science and Engineering, Sun Yat-sen University · Shenzhen Loop Area Institute · Southern University of Science and Technology
Dropout Robustness and Cognitive Profiling of Transformer Models via Stochastic Inference
Mar 18, 2026Antônio Junior Alves Caiado, Michael HahslerMonte Carlo Dropout Language Model Robustness
Lyle School of Engineering, Southern Methodist University, Dallas, TX, USA

Apr 3, 2026J/K move · Enter open · S save

Evolutionary Search for Automated Design of Uncertainty Quantification Methods

Mikhail Seleznyov, Daniil Korbut, Viktor Moskvoretskii, Oleg Somov+2

AIRI · Skoltech · Amazon+2

Uncertainty Quantification LLM Uncertainty Estimation LLM Hallucination Detection Large Language Model-Guided Optimization Evolutionary Optimization

Open paper AskPDF arXiv

Uncertainty quantification (UQ) methods for large language models are predominantly designed by hand based on domain knowledge and heuristics, limiting their scalability and generality. We apply LLM-powered evolutionary search to automatically discover unsupervised UQ methods represented as Python programs. On the task of atomic claim verification, our evolved methods outperform strong manually-designed baselines, achieving up to 6.7% relative ROC-AUC improvement across 9 datasets while generalizing robustly out-of-distribution. Qualitative analysis reveals that different LLMs employ qualitatively distinct evolutionary strategies: Claude models consistently design high-feature-count linear estimators, while Gpt-oss-120B gravitates toward simpler and more interpretable positional weighting schemes. Surprisingly, only Sonnet 4.5 and Opus 4.5 reliably leverage increased method complexity to improve performance -- Opus 4.6 shows an unexpected regression relative to its predecessor. Overall, our results indicate that LLM-powered evolutionary search is a promising paradigm for automated, interpretable hallucination detector design.