mlsanityData to 14 Oct 2026

Benchmarking LLMs via Uncertainty Quantification

arXiv 2401.12794 ↗First posted 23 Jan 2024cs.CLcited by 126

Not on the map. Why?

Abstract (arXiv)

The proliferation of open-source Large Language Models (LLMs) from various institutions has highlighted the urgent need for comprehensive evaluation methods. However, current evaluation platforms, such as the widely recognized HuggingFace open LLM leaderboard, neglect a crucial aspect -- uncertainty, which is vital for thoroughly assessing LLMs. To bridge this gap, we introduce a new benchmarking approach for LLMs that integrates uncertainty quantification. Our examination involves nine LLMs (LLM series) spanning five representative natural language processing tasks. Our findings reveal that: I) LLMs with higher accuracy may exhibit lower certainty; II) Larger-scale LLMs may display greater uncertainty compared to their smaller counterparts; and III) Instruction-finetuning tends to increase the uncertainty of LLMs. These results underscore the significance of incorporating uncertainty in the evaluation of LLMs.

Key facts. Cited by 126 papers in the map (data through 14 Oct 2026). Builds on 52 of its 87 references that are in the map. First posted on arXiv 23 Jan 2024.

Builds on

52 of 87 references.

References · 52

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  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. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  5. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  6. 2017On Calibration of Modern Neural Networkscited by 4,960
  7. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,100
  8. 2023Qwen Technical Reportcited by 3,344
  9. 2023Mistral 7Bcited by 3,164
  10. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  11. 2023A Survey of Large Language Modelscited by 2,576
  12. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,292
38 more
  1. 2023A Survey on Evaluation of Large Language Modelscited by 1,242
  2. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 974
  3. 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 938
  4. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 819
  5. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 819
  6. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 792
  7. 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
  8. 2023A Comprehensive Overview of Large Language Modelscited by 648
  9. 2021BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generationcited by 412
  10. 2023Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyondcited by 411
  11. 2020Classification with Valid and Adaptive Coveragecited by 396
  12. 2021Revisiting the Calibration of Modern Neural Networkscited by 390
  13. 2020Uncertainty Sets for Image Classifiers using Conformal Predictioncited by 366
  14. 2023HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Modelscited by 341
  15. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 293
  16. 2019Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoningcited by 285
  17. 2016Least Ambiguous Set-Valued Classifiers with Bounded Error Levelscited by 272
  18. 2023Challenges and Applications of Large Language Modelscited by 254
  19. 2020Unsupervised Quality Estimation for Neural Machine Translationcited by 211
  20. 2023Evaluating Large Language Models: A Comprehensive Surveycited by 202
  21. 2023FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Setscited by 201
  22. 2023SafetyBench: Evaluating the Safety of Large Language Modelscited by 199
  23. 2023Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integrationcited by 172
  24. 2023Conformal Language Modelingcited by 170
  25. 2020Uncertainty Quantification and Deep Ensemblescited by 139
  26. 2023Conformal Prediction with Large Language Models for Multi-Choice Question Answeringcited by 139
  27. 2023LM-Polygraph: Uncertainty Estimation for Language Modelscited by 131
  28. 2020Conformal Prediction: a Unified Review of Theory and New Challengescited by 118
  29. 2023Enhancing Conversational Search: Large Language Model-Aided Informative Query Rewritingcited by 69
  30. 2023FELM: Benchmarking Factuality Evaluation of Large Language Modelscited by 66
  31. 2023Federated Conformal Predictors for Distributed Uncertainty Quantificationcited by 46
  32. 2023Uncertainty in Natural Language Processing: Sources, Quantification, and Applicationscited by 44
  33. 2023Conformal Nucleus Samplingcited by 33
  34. 2023Improving the Reliability of Large Language Models by Leveraging Uncertainty-Aware In-Context Learningcited by 29
  35. 2023A Comprehensive Evaluation of GPT-4V on Knowledge-Intensive Visual Question Answeringcited by 23
  36. 2021Conformal prediction for text infilling and part-of-speech predictioncited by 22
  37. 2023Retrieval-augmented Multi-modal Chain-of-Thoughts Reasoning for Large Language Modelscited by 18
  38. 2024Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Modelscited by 17

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 35; 2025: 48; 2026: 43.

126 papers.

Sort:

By area:

  1. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 172
  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. 2024Large language model validity via enhanced conformal prediction methodscited by 92
  5. 2024On Verbalized Confidence Scores for LLMscited by 83
  6. 2024ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guaranteescited by 65
  7. 2025GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoningcited by 58
  8. 2024Conformal Alignment: Knowing When to Trust Foundation Models with Guaranteescited by 54
  9. 2024Conformal Prediction for Natural Language Processing: A Surveycited by 53
  10. 2024Internal Consistency and Self-Feedback in Large Language Models: A Surveycited by 50
  11. 2024Knowledge Boundary of Large Language Models: A Surveycited by 40
  12. 2025Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Surveycited by 30
38 more
  1. 2024Uncertainty-Aware Evaluation for Vision-Language Modelscited by 29
  2. 2024Evaluating language models as risk scorescited by 27
  3. 2024MAQA: Evaluating Uncertainty Quantification in LLMs Regarding Data Uncertaintycited by 27
  4. 2024Do LLMs estimate uncertainty well in instruction-following?cited by 26
  5. 2025LLM Probability Concentration: How Alignment Shrinks the Generative Horizoncited by 26
  6. 2024Conformal Prediction: A Data Perspectivecited by 25
  7. 2024GPT-4 vs. Human Translators: A Comprehensive Evaluation of Translation Quality Across Languages, Domains, and Expertise Levelscited by 21
  8. 2025Learning Conformal Abstention Policies for Adaptive Risk Management in Large Language and Vision-Language Modelscited by 21
  9. 2024xFinder: Large Language Models as Automated Evaluators for Reliable Evaluationcited by 19
  10. 2024Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Modelscited by 19
  11. 2024Prune 'n Predict: Optimizing LLM Decision-making with Conformal Predictioncited by 18
  12. 2025E-valuator: Reliable Agent Verifiers with Sequential Hypothesis Testingcited by 17
  13. 2024Towards Rationality in Language and Multimodal Agents: A Surveycited by 16
  14. 2024Probabilistic Medical Predictions of Large Language Modelscited by 16
  15. 2024UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generationcited by 16
  16. 2024See What LLMs Cannot Answer: A Self-Challenge Framework for Uncovering LLM Weaknessescited by 15
  17. 2024Addressing Uncertainty in LLMs to Enhance Reliability in Generative AIcited by 15
  18. 2025An overview of model uncertainty and variability in LLM-based sentiment analysis. Challenges, mitigation strategies and the role of explainabilitycited by 15
  19. 2026Knowing When to Abstain: Medical LLMs Under Clinical Uncertaintycited by 15
  20. 2024Large Language Model Confidence Estimation via Black-Box Accesscited by 14
  21. 2024Uncertainty Quantification in Large Language Models Through Convex Hull Analysiscited by 13
  22. 2024Uncertainty is Fragile: Manipulating Uncertainty in Large Language Modelscited by 13
  23. 2024Anchor-based Large Language Modelscited by 12
  24. 2025Seeing and Reasoning with Confidence: Supercharging Multimodal LLMs with an Uncertainty-Aware Agentic Frameworkcited by 12
  25. 2025Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident, Especially When They are Wrongcited by 11
  26. 2024Graph-based Confidence Calibration for Large Language Modelscited by 10
  27. 2025Probabilistic Stability Guarantees for Feature Attributionscited by 9
  28. 2025Statistical Multicriteria Evaluation of LLM-Generated Textcited by 9
  29. 2025ReasonBENCH: Benchmarking the (In)Stability of LLM Reasoningcited by 9
  30. 2024Ranking Large Language Models without Ground Truthcited by 8
  31. 2024Are Large Language Models Chameleons? An Attempt to Simulate Social Surveyscited by 8
  32. 2025Calibrating Uncertainty Quantification of Multi-Modal LLMs using Groundingcited by 8
  33. 2026Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failurescited by 8
  34. 2024UBench: Benchmarking Uncertainty in Large Language Models with Multiple Choice Questionscited by 7
  35. 2025FailureSensorIQ: A Multi-Choice QA Dataset for Understanding Sensor Relationships and Failure Modescited by 7
  36. 2025Conformal Information Pursuit for Interactively Guiding Large Language Modelscited by 7
  37. 2024PRobELM: Plausibility Ranking Evaluation for Language Modelscited by 6
  38. 2024Enhancing Healthcare LLM Trust with Atypical Presentations Recalibrationcited by 6

50 most cited of 126 All 126 (JSON)