mlsanityData to 7 Oct 2026

How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering

arXiv 2012.00955 ↗First posted 2 Dec 2020cs.CLcited by 439

Not on the map. Why?

Cited by 30 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recent works have shown that language models (LM) capture different types of knowledge regarding facts or common sense. However, because no model is perfect, they still fail to provide appropriate answers in many cases. In this paper, we ask the question "how can we know when language models know, with confidence, the answer to a particular query?" We examine this question from the point of view of calibration, the property of a probabilistic model's predicted probabilities actually being well correlated with the probabilities of correctness. We examine three strong generative models -- T5, BART, and GPT-2 -- and study whether their probabilities on QA tasks are well calibrated, finding the answer is a relatively emphatic no. We then examine methods to calibrate such models to make their confidence scores correlate better with the likelihood of correctness through fine-tuning, post-hoc probability modification, or adjustment of the predicted outputs or inputs. Experiments on a diverse range of datasets demonstrate the effectiveness of our methods. We also perform analysis to study the strengths and limitations of these methods, shedding light on further improvements that may be made in methods for calibrating LMs. We have released the code at https://github.com/jzbjyb/lm-calibration.

Key facts. Cited by 439 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 38; 2023: 89; 2024: 124; 2025: 96; 2026: 85.

439 papers.

Sort:

By area:

  1. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  2. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  3. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 946
  4. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 795
  5. 2022Teaching Models to Express Their Uncertainty in Wordscited by 731
  6. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  7. 2023Active Retrieval Augmented Generationcited by 506
  8. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 457
  9. 2023Large Language Models Are Not Robust Multiple Choice Selectorscited by 454
  10. 2023Cognitive Architectures for Language Agentscited by 422
  11. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  12. 2023Large Language Models for Information Retrieval: A Surveycited by 331
38 more
  1. 2023Robots That Ask For Help: Uncertainty Alignment for Large Language Model Plannerscited by 298
  2. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 286
  3. 2022Prompting GPT-3 To Be Reliablecited by 258
  4. 2023A Survey of Confidence Estimation and Calibration in Large Language Modelscited by 253
  5. 2023Self-Evaluation Guided Beam Search for Reasoningcited by 195
  6. 2024Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaborationcited by 176
  7. 2022Language models show human-like content effects on reasoning taskscited by 171
  8. 2023Personality Traits in Large Language Modelscited by 166
  9. 2023Conformal Language Modelingcited by 163
  10. 2023Foundation Models for Decision Making: Problems, Methods, and Opportunitiescited by 160
  11. 2023GPT-NER: Named Entity Recognition via Large Language Modelscited by 158
  12. 2024Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similaritiescited by 156
  13. 2023LM vs LM: Detecting Factual Errors via Cross Examinationcited by 155
  14. 2022The 'Problem' of Human Label Variation: On Ground Truth in Data, Modeling and Evaluationcited by 133
  15. 2023Conformal Prediction with Large Language Models for Multi-Choice Question Answeringcited by 131
  16. 2023AI Transparency in the Age of LLMs: A Human-Centered Research Roadmapcited by 119
  17. 2024Know Your Limits: A Survey of Abstention in Large Language Modelscited by 116
  18. 2024Language Model Cascades: Token-level uncertainty and beyondcited by 115
  19. 2023Calibrated Language Models Must Hallucinatecited by 114
  20. 2023Decomposing Uncertainty for Large Language Models through Input Clarification Ensemblingcited by 113
  21. 2023Bayesian Low-rank Adaptation for Large Language Modelscited by 112
  22. 2024What Large Language Models Know and What People Think They Knowcited by 109
  23. 2024Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertaintycited by 106
  24. 2024Why Tabular Foundation Models Should Be a Research Prioritycited by 103
  25. 2024The Art of Saying No: Contextual Noncompliance in Language Modelscited by 100
  26. 2024AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attackscited by 94
  27. 2025Uncertainty Quantification and Confidence Calibration in Large Language Models: A Surveycited by 93
  28. 2023Navigating the Grey Area: How Expressions of Uncertainty and Overconfidence Affect Language Modelscited by 91
  29. 2023Crawling the Internal Knowledge-Base of Language Modelscited by 85
  30. 2024On Verbalized Confidence Scores for LLMscited by 83
  31. 2022Meaning without reference in large language modelscited by 76
  32. 2023On the Calibration of Large Language Models and Alignmentcited by 72
  33. 2023Alignment for Honestycited by 72
  34. 2024Calibrating Large Language Models with Sample Consistencycited by 72
  35. 2022On the Relation between Sensitivity and Accuracy in In-context Learningcited by 71
  36. 2022Stop Measuring Calibration When Humans Disagreecited by 70
  37. 2022Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial Settingscited by 66
  38. 2024Can multiple-choice questions really be useful in detecting the abilities of LLMs?cited by 66

50 most cited of 439 All 439 (JSON)