mlsanityData to 7 Oct 2026

Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models

arXiv 2305.19187 ↗First posted 30 May 2023cs.CL cs.LG stat.MLcited by 286

Not on the map. Why?

Cited by 43 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Large language models (LLMs) specializing in natural language generation (NLG) have recently started exhibiting promising capabilities across a variety of domains. However, gauging the trustworthiness of responses generated by LLMs remains an open challenge, with limited research on uncertainty quantification (UQ) for NLG. Furthermore, existing literature typically assumes white-box access to language models, which is becoming unrealistic either due to the closed-source nature of the latest LLMs or computational constraints. In this work, we investigate UQ in NLG for *black-box* LLMs. We first differentiate *uncertainty* vs *confidence*: the former refers to the ``dispersion'' of the potential predictions for a fixed input, and the latter refers to the confidence on a particular prediction/generation. We then propose and compare several confidence/uncertainty measures, applying them to *selective NLG* where unreliable results could either be ignored or yielded for further assessment. Experiments were carried out with several popular LLMs on question-answering datasets (for evaluation purposes). Results reveal that a simple measure for the semantic dispersion can be a reliable predictor of the quality of LLM responses, providing valuable insights for practitioners on uncertainty management when adopting LLMs. The code to replicate our experiments is available at https://github.com/zlin7/UQ-NLG.

Key facts. Cited by 286 papers in the map (data through 7 Oct 2026). Builds on 38 of its 68 references that are in the map. First posted on arXiv 30 May 2023.

Builds on

38 of 68 references.

References · 38

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  6. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  7. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  8. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
  9. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  10. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  11. 2015A large annotated corpus for learning natural language inferencecited by 1,837
  12. 2022Language Models (Mostly) Know What They Knowcited by 1,783
26 more
  1. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  2. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 813
  3. 2017Selective Classification for Deep Neural Networkscited by 799
  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. 2018CoQA: A Conversational Question Answering Challengecited by 674
  7. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  8. 2019Measuring Calibration in Deep Learningcited by 443
  9. 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 439
  10. 2020Calibration of Pre-trained Transformerscited by 307
  11. 2022Confident Adaptive Language Modelingcited by 297
  12. 2015Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networkscited by 295
  13. 2022Prompting GPT-3 To Be Reliablecited by 258
  14. 2020Selective Question Answering under Domain Shiftcited by 228
  15. 2020Reducing conversational agents' overconfidence through linguistic calibrationcited by 209
  16. 2018To Trust Or Not To Trust A Classifiercited by 205
  17. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 193
  18. 2019Addressing Failure Prediction by Learning Model Confidencecited by 183
  19. 2021DEUP: Direct Epistemic Uncertainty Predictioncited by 102
  20. 2022Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial Settingscited by 66
  21. 2020Trust Issues: Uncertainty Estimation Does Not Enable Reliable OOD Detection On Medical Tabular Datacited by 52
  22. 2023What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variabilitycited by 51
  23. 2022Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Taskscited by 49
  24. 2023Post-Abstention: Towards Reliably Re-Attempting the Abstained Instances in QAcited by 20
  25. 2020Towards Improving Selective Prediction Ability of NLP Systemscited by 19
  26. 2021SCRIB: Set-classifier with Class-specific Risk Bounds for Blackbox Modelscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 17; 2024: 75; 2025: 102; 2026: 92.

286 papers.

Sort:

By area:

  1. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  2. 2024INSIDE: LLMs' Internal States Retain the Power of Hallucination Detectioncited by 317
  3. 2023Exploring the Potential of Large Language Models (LLMs) in Learning on Graphscited by 271
  4. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 236
  5. 2024Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similaritiescited by 156
  6. 2024Benchmarking LLMs via Uncertainty Quantificationcited by 124
  7. 2023Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthinesscited by 121
  8. 2024To Believe or Not to Believe Your LLMcited by 120
  9. 2024Know Your Limits: A Survey of Abstention in Large Language Modelscited by 116
  10. 2024Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methodscited by 114
  11. 2023Decomposing Uncertainty for Large Language Models through Input Clarification Ensemblingcited by 113
  12. 2024Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraphcited by 105
38 more
  1. 2024Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreementcited by 99
  2. 2024HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detectioncited by 96
  3. 2024On Verbalized Confidence Scores for LLMscited by 83
  4. 2025SAFE: Multitask Failure Detection for Vision-Language-Action Modelscited by 74
  5. 2024Learning to Route LLMs with Confidence Tokenscited by 66
  6. 2023Uncertainty in Natural Language Generation: From Theory to Applicationscited by 61
  7. 2024Mitigating LLM Hallucinations via Conformal Abstentioncited by 56
  8. 2024Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluationcited by 56
  9. 2025GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoningcited by 56
  10. 2024Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinationscited by 51
  11. 2024Conformal Alignment: Knowing When to Trust Foundation Models with Guaranteescited by 50
  12. 2024Internal Consistency and Self-Feedback in Large Language Models: A Surveycited by 49
  13. 2025Steer LLM Latents for Hallucination Detectioncited by 49
  14. 2025A Survey of Large Language Model Agents for Question Answeringcited by 46
  15. 2024MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMscited by 45
  16. 2024Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimensioncited by 45
  17. 2024Multicalibration for Confidence Scoring in LLMscited by 44
  18. 2025UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Makingcited by 36
  19. 2024Uncertainty quantification in fine-tuned LLMs using LoRA ensemblescited by 35
  20. 2024Improving Uncertainty Estimation through Semantically Diverse Language Generationcited by 34
  21. 2025Uncertainty Quantification for LLMs through Minimum Bayes Risk: Bridging Confidence and Consistencycited by 30
  22. 2024Towards Uncertainty-Aware Language Agentcited by 29
  23. 2024Confidence Calibration and Rationalization for LLMs via Multi-Agent Deliberationcited by 26
  24. 2025Estimating LLM Uncertainty with Evidencecited by 26
  25. 2025Exploring the Roles of Large Language Models in Reshaping Transportation Systems: A Survey, Framework, and Roadmapcited by 26
  26. 2024Evaluating language models as risk scorescited by 24
  27. 2025Understanding the Uncertainty of LLM Explanations: A Perspective Based on Reasoning Topologycited by 24
  28. 2025TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoningcited by 24
  29. 2025BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMscited by 23
  30. 2024Scalable Qualitative Coding with LLMs: Chain-of-Thought Reasoning Matches Human Performance in Some Hermeneutic Taskscited by 22
  31. 2024Unveiling the Tapestry of Consistency in Large Vision-Language Modelscited by 22
  32. 2025Revisiting Uncertainty Estimation and Calibration of Large Language Modelscited by 22
  33. 2024A Survey on the Honesty of Large Language Modelscited by 21
  34. 2025From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centeredcited by 21
  35. 2023Investigating Uncertainty Calibration of Aligned Language Models under the Multiple-Choice Settingcited by 20
  36. 2024DeLLMa: Decision Making Under Uncertainty with Large Language Modelscited by 20
  37. 2024Estimating the Hallucination Rate of Generative AIcited by 20
  38. 2025Conformal Linguistic Calibration: Trading-off between Factuality and Specificitycited by 20

50 most cited of 286 All 286 (JSON)