mlsanityData to 14 Oct 2026

Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph

arXiv 2406.15627 ↗First posted 21 Jun 2024cs.CL cs.LGcited by 105

Not on the map. Why?

Abstract (arXiv)

The rapid proliferation of large language models (LLMs) has stimulated researchers to seek effective and efficient approaches to deal with LLM hallucinations and low-quality outputs. Uncertainty quantification (UQ) is a key element of machine learning applications in dealing with such challenges. However, research to date on UQ for LLMs has been fragmented in terms of techniques and evaluation methodologies. In this work, we address this issue by introducing a novel benchmark that implements a collection of state-of-the-art UQ baselines and offers an environment for controllable and consistent evaluation of novel UQ techniques over various text generation tasks. Our benchmark also supports the assessment of confidence normalization methods in terms of their ability to provide interpretable scores. Using our benchmark, we conduct a large-scale empirical investigation of UQ and normalization techniques across eleven tasks, identifying the most effective approaches. Code: https://github.com/IINemo/lm-polygraph Benchmark: https://huggingface.co/LM-Polygraph

Key facts. Cited by 105 papers in the map (data through 14 Oct 2026). Builds on 50 of its 89 references that are in the map. First posted on arXiv 21 Jun 2024.

Builds on

50 of 89 references.

References · 50

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  5. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  6. 2023Mistral 7Bcited by 3,164
  7. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  8. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  9. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  10. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,653
  11. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  12. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,317
38 more
  1. 2020COMET: A Neural Framework for MT Evaluationcited by 1,033
  2. 2023Accelerating Large Language Model Decoding with Speculative Samplingcited by 1,006
  3. 2017Deep Bayesian Active Learning with Image Datacited by 819
  4. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 819
  5. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 812
  6. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 810
  7. 2018CoQA: A Conversational Question Answering Challengecited by 683
  8. 2020DeeBERT: Dynamic Early Exiting for Accelerating BERT Inferencecited by 332
  9. 2022Confident Adaptive Language Modelingcited by 310
  10. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 293
  11. 2023AlignScore: Evaluating Factual Consistency with a Unified Alignment Functioncited by 288
  12. 2020Unsupervised Quality Estimation for Neural Machine Translationcited by 211
  13. 2020Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learningcited by 210
  14. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 197
  15. 2018Understanding Measures of Uncertainty for Adversarial Example Detectioncited by 177
  16. 2021On Hallucination and Predictive Uncertainty in Conditional Language Generationcited by 176
  17. 2024Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantificationcited by 162
  18. 2023Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Modelscited by 150
  19. 2022On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?cited by 138
  20. 2023LM-Polygraph: Uncertainty Estimation for Language Modelscited by 131
  21. 2020The Right Tool for the Job: Matching Model and Instance Complexitiescited by 126
  22. 2023Enhancing Uncertainty-Based Hallucination Detection with Stronger Focuscited by 99
  23. 2024Stable LM 2 1.6B Technical Reportcited by 90
  24. 2024LUQ: Long-text Uncertainty Quantification for LLMscited by 81
  25. 2021Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detectioncited by 70
  26. 2023Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Modelscited by 69
  27. 2022Mutual Information Alleviates Hallucinations in Abstractive Summarizationcited by 68
  28. 2023Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspectioncited by 44
  29. 2021Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimatescited by 39
  30. 2022Nonparametric Uncertainty Quantification for Single Deterministic Neural Networkcited by 36
  31. 2022Detection of Word Adversarial Examples in Text Classification: Benchmark and Baseline via Robust Density Estimationcited by 32
  32. 2019Mitigating Uncertainty in Document Classificationcited by 22
  33. 2022Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Datacited by 21
  34. 2024Quantifying Aleatoric and Epistemic Uncertainty with Proper Scoring Rulescited by 21
  35. 2024Vikhr: The Family of Open-Source Instruction-Tuned Large Language Models for Russiancited by 12
  36. 2022Towards Computationally Feasible Deep Active Learningcited by 11
  37. 2017Centered Isotonic Regression: Point and Interval Estimation for Dose-Response Studiescited by 5
  38. 2023Scalable Batch Acquisition for Deep Bayesian Active Learningcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 8; 2025: 47; 2026: 50.

105 papers.

Sort:

By area:

  1. 2025AbstentionBench: Reasoning LLMs Fail on Unanswerable Questionscited by 145
  2. 2024A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directionscited by 121
  3. 2025Uncertainty Quantification and Confidence Calibration in Large Language Models: A Surveycited by 95
  4. 2025Uncertainty Quantification for LLMs through Minimum Bayes Risk: Bridging Confidence and Consistencycited by 30
  5. 2025Beyond Semantic Entropy: Boosting LLM Uncertainty Quantification with Pairwise Semantic Similaritycited by 28
  6. 2025TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoningcited by 24
  7. 2025A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputscited by 21
  8. 2024Rethinking Uncertainty Estimation in LLMs: A Principled Single-Sequence Measurecited by 18
  9. 2025Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Modelscited by 18
  10. 2025Uncertainty Quantification of Large Language Models through Multi-Dimensional Responsescited by 18
  11. 2025Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorerscited by 18
  12. 2025The Illusion of Certainty: Uncertainty Quantification for LLMs Fails under Ambiguitycited by 17
38 more
  1. 2025Efficient Hallucination Detection for LLMs Using Uncertainty-Aware Attention Headscited by 16
  2. 2025Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Modelscited by 16
  3. 2025Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?cited by 16
  4. 2026Knowing When to Abstain: Medical LLMs Under Clinical Uncertaintycited by 15
  5. 2025Query-Level Uncertainty in Large Language Modelscited by 14
  6. 2025Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missingcited by 14
  7. 2025When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQAcited by 14
  8. 2024Multi-group Uncertainty Quantification for Long-form Text Generationcited by 13
  9. 2025Thinking Out Loud: Do Reasoning Models Know When They're Right?cited by 12
  10. 2025MMBoundary: Advancing MLLM Knowledge Boundary Awareness through Reasoning Step Confidence Calibrationcited by 11
  11. 2025Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directionscited by 11
  12. 2024ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertaintycited by 10
  13. 2026Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantificationcited by 10
  14. 2024Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Modelscited by 9
  15. 2025UQLM: A Python Package for Uncertainty Quantification in Large Language Modelscited by 9
  16. 2026ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spacescited by 8
  17. 2024MORTAR: Multi-turn Metamorphic Testing for LLM-based Dialogue Systemscited by 7
  18. 2025Addressing Pitfalls in the Evaluation of Uncertainty Estimation Methods for Natural Language Generationcited by 7
  19. 2025Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question-Answeringcited by 7
  20. 2025Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Predictioncited by 7
  21. 2026ReDAct: Uncertainty-Aware Deferral for LLM Agentscited by 7
  22. 2025Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval Augmented Generationcited by 6
  23. 2025Inv-Entropy: A Fully Probabilistic Framework for Uncertainty Quantification in Language Modelscited by 6
  24. 2025CoCoLex: Confidence-guided Copy-based Decoding for Grounded Legal Text Generationcited by 6
  25. 2025Mitigating Lost in Multi-turn Conversation via Curriculum RL with Verifiable Accuracy and Abstention Rewardscited by 6
  26. 2026LLMs Should Express Uncertainty Explicitlycited by 6
  27. 2024Enhancing Trust in Large Language Models via Uncertainty-Calibrated Fine-Tuningcited by 5
  28. 2025UNCERTAINTY-LINE: Length-Invariant Estimation of Uncertainty for Large Language Modelscited by 5
  29. 2025Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QAcited by 5
  30. 2025HEDGE: Hallucination Estimation via Dense Geometric Entropy for VQA with Vision-Language Modelscited by 5
  31. 2026The Cost of Reasoning: Chain-of-Thought Induces Overconfidence in Vision-Language Modelscited by 5
  32. 2026Geometry-Calibrated Conformal Abstention for Language Modelscited by 5
  33. 2024Enhancing Zero-shot Chain of Thought Prompting via Uncertainty-Guided Strategy Selectioncited by 4
  34. 2025MCQA-Eval: Efficient Confidence Evaluation in NLG with Gold-Standard Correctness Labelscited by 4
  35. 2025RePPL: Recalibrating Perplexity by Uncertainty in Semantic Propagation and Language Generation for Explainable QA Hallucination Detectioncited by 4
  36. 2025Can LLMs Make (Personalized) Access Control Decisions?cited by 4
  37. 2026Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Studycited by 4
  38. 2025Self-Reported Confidence of Large Language Models in Gastroenterology: Analysis of Commercial, Open-Source, and Quantized Modelscited by 3

50 most cited of 105 All 105 (JSON)