mlsanityData to 14 Oct 2026

Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey

arXiv 2503.15850 ↗First posted 20 Mar 2025cs.CLcited by 95

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

Large Language Models (LLMs) excel in text generation, reasoning, and decision-making, enabling their adoption in high-stakes domains such as healthcare, law, and transportation. However, their reliability is a major concern, as they often produce plausible but incorrect responses. Uncertainty quantification (UQ) enhances trustworthiness by estimating confidence in outputs, enabling risk mitigation and selective prediction. However, traditional UQ methods struggle with LLMs due to computational constraints and decoding inconsistencies. Moreover, LLMs introduce unique uncertainty sources, such as input ambiguity, reasoning path divergence, and decoding stochasticity, that extend beyond classical aleatoric and epistemic uncertainty. To address this, we introduce a new taxonomy that categorizes UQ methods based on computational efficiency and uncertainty dimensions (input, reasoning, parameter, and prediction uncertainty). We evaluate existing techniques, assess their real-world applicability, and identify open challenges, emphasizing the need for scalable, interpretable, and robust UQ approaches to enhance LLM reliability.

Key facts. Cited by 95 papers in the map (data through 14 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 104 of its 166 references that are in the map. First posted on arXiv 20 Mar 2025.

Builds on

104 of 166 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-Thought24 Feb
  2. 2024Cycles of Thought: Measuring LLM Confidence through Stable Explanations5 Jun
  3. 2023Self-Refine: Iterative Refinement with Self-Feedback30 Mar
  4. 2022Language Models (Mostly) Know What They Know11 Jul

Other references · 100

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  6. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  7. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,100
  8. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  9. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  10. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  11. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  12. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
38 more
  1. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  2. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
  3. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  4. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,356
  5. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  6. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 974
  7. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
  8. 2017RACE: Large-scale ReAding Comprehension Dataset From Examinationscited by 861
  9. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 812
  10. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 810
  11. 2022Teaching Models to Express Their Uncertainty in Wordscited by 751
  12. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  13. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 732
  14. 2024LLM Evaluators Recognize and Favor Their Own Generationscited by 686
  15. 2018CoQA: A Conversational Question Answering Challengecited by 683
  16. 2023The Internal State of an LLM Knows When It's Lyingcited by 659
  17. 2018Predictive Uncertainty Estimation via Prior Networkscited by 557
  18. 2023Large Language Models Are Not Robust Multiple Choice Selectorscited by 486
  19. 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 445
  20. 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 390
  21. 2023A Survey of Hallucination in Large Foundation Modelscited by 368
  22. 2021Measuring and Improving Consistency in Pretrained Language Modelscited by 364
  23. 2023HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Modelscited by 341
  24. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 334
  25. 2019Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoningcited by 285
  26. 2020Reducing conversational agents' overconfidence through linguistic calibrationcited by 210
  27. 2022Knowledge Distillation from A Stronger Teachercited by 208
  28. 2018To Trust Or Not To Trust A Classifiercited by 207
  29. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 197
  30. 2019Addressing Failure Prediction by Learning Model Confidencecited by 186
  31. 2022ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoningcited by 177
  32. 2023Conformal Language Modelingcited by 170
  33. 2024Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantificationcited by 162
  34. 2024Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similaritiescited by 159
  35. 2023Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Modelscited by 150
  36. 2023Conformal Prediction with Large Language Models for Multi-Choice Question Answeringcited by 139
  37. 2023LM-Polygraph: Uncertainty Estimation for Language Modelscited by 131
  38. 2024Simulating Classroom Education with LLM-Empowered Agentscited by 127

50 most cited of 100 All 100 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 31; 2026: 64.

95 papers.

Sort:

By area:

  1. 2025LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directionscited by 50
  2. 2025Unlocking Exploration in RLVR: Uncertainty-aware Advantage Shaping for Deeper Reasoningcited by 34
  3. 2025BroRL: Scaling Reinforcement Learning via Broadened Explorationcited by 25
  4. 2025TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoningcited by 24
  5. 2025Metacognition and Uncertainty Communication in Humans and Large Language Modelscited by 23
  6. 2025Revisiting Uncertainty Estimation and Calibration of Large Language Modelscited by 23
  7. 2025From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centeredcited by 21
  8. 2026Intelligent AI Delegationcited by 18
  9. 2025The Illusion of Certainty: Uncertainty Quantification for LLMs Fails under Ambiguitycited by 17
  10. 2025Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMscited by 13
  11. 2025Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCRcited by 12
  12. 2025Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safetycited by 12
38 more
  1. 2025Learned Hallucination Detection in Black-Box LLMs using Token-level Entropy Production Ratecited by 10
  2. 2025Generalizability of Large Language Model-Based Agents: A Comprehensive Surveycited by 10
  3. 2026The Illusion of Stochasticity in LLMscited by 9
  4. 2025Estimating Semantic Alphabet Size for LLM Uncertainty Quantificationcited by 8
  5. 2025LEC: Linear Expectation Constraints for Selection-Conditioned Risk Control in Selective Prediction and Routing Systemscited by 7
  6. 2026LLMs as Signal Detectors: Sensitivity, Bias, and the Temperature-Criterion Analogycited by 7
  7. 2025Uncertainty Quantification for Retrieval-Augmented Reasoningcited by 6
  8. 2026SafeGround: Know When to Trust GUI Grounding Models via Uncertainty Calibrationcited by 6
  9. 2026Overconfidence and Calibration in Medical VQA: Empirical Findings and Hallucination-Aware Mitigationcited by 6
  10. 2025Do Large Language Models (Really) Need Statistical Foundations?cited by 5
  11. 2025Knowing What You Know Is Not Enough: Large Language Model Confidences Don't Align With Their Actionscited by 4
  12. 2026Semantic Self-Distillation for Language Model Uncertaintycited by 4
  13. 2025Organ-Agents: Virtual Human Physiology Simulator via LLMscited by 3
  14. 2026Task-Awareness Improves LLM Generations and Uncertaintycited by 3
  15. 2026Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Modelscited by 3
  16. 2026Real-Time Trustworthiness Scoring for LLM Structured Outputs and Data Extractioncited by 3
  17. 2026Drift is a Sampling Error: SNR-Aware Power Distributions for Long-Horizon Robotic Planningcited by 3
  18. 2026Compress the Context, Keep the Commitments: A Formal Framework for Verifiable LLM Context Compressioncited by 3
  19. 2026When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based Multi-Agent Systemscited by 3
  20. 2025ChemAU: Harness the Reasoning of LLMs in Chemical Research with Adaptive Uncertainty Estimationcited by 2
  21. 2025Shall We Play a Game? Language Models for Open-ended Wargamescited by 2
  22. 2025Conf-Profile: A Confidence-Driven Reasoning Paradigm for Label-Free User Profilingcited by 2
  23. 2025Multicalibration for LLM-based Code Generationcited by 2
  24. 2026Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Modelscited by 2
  25. 2026How Open Must Language Models be to Enable Reliable Scientific Inference?cited by 2
  26. 2026Process Supervision of Confidence Margin for Calibrated LLM Reasoningcited by 2
  27. 2026Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attributioncited by 2
  28. 2026Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Predictioncited by 2
  29. 2026A Systematic Evaluation of Black-Box Uncertainty Estimation Methods for Large Language Modelscited by 2
  30. 2026BaRA: Bayesian Adaptive Rank Allocation for Parameter-Efficient Fine-Tuningcited by 2
  31. 2026The "I Don't Know" Filter: Enhancing Agentic Reliability in Function Callingcited by 2
  32. 2026ConfidenceBench: Evaluating Confidence Calibration in Large Language Modelscited by 2
  33. 2025GE-Chat: A Graph Enhanced RAG Framework for Evidential Response Generation of LLMscited by 1
  34. 2025Dist2ill: Distributional Distillation for One-Pass Uncertainty Estimation in Large Language Modelscited by 1
  35. 2025Uncertainty-aware Reward Design Processcited by 1
  36. 2025EgoLoc: A Generalizable Solution for Temporal Interaction Localization in Egocentric Videoscited by 1
  37. 2025CryptoQA: A Large-scale Question-answering Dataset for AI-assisted Cryptographycited by 1
  38. 2026Judging with Personality and Confidence: A Study on Personality-Conditioned LLM Relevance Assessmentcited by 1

50 most cited of 95 All 95 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026The Origins of Stochasticity: Comprehensive Investigations on Uncertainty Quantification for Large Language Models
  2. 2026ChainUQ: Reasoning Consistency-Aware Uncertainty Quantification for Large Language Models
  3. 2026Uncertainty Quantification for LLM Function-Calling
  4. 2024UBench: Benchmarking Uncertainty in Large Language Models with Multiple Choice Questions
  5. 2024Rethinking the Uncertainty: A Critical Review and Analysis in the Era of Large Language Models
  6. 2024On Verbalized Confidence Scores for LLMs
  7. 2025Can Linear Probes Measure LLM Uncertainty?
  8. 2026Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities