mlsanityData to 7 Oct 2026

On Verbalized Confidence Scores for LLMs

arXiv 2412.14737 ↗First posted 19 Dec 2024cs.CLcited by 83

Not on the map. Why?

Cited by 25 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The rise of large language models (LLMs) and their tight integration into our daily life make it essential to dedicate efforts towards their trustworthiness. Uncertainty quantification for LLMs can establish more human trust into their responses, but also allows LLM agents to make more informed decisions based on each other's uncertainty. To estimate the uncertainty in a response, internal token logits, task-specific proxy models, or sampling of multiple responses are commonly used. This work focuses on asking the LLM itself to verbalize its uncertainty with a confidence score as part of its output tokens, which is a promising way for prompt- and model-agnostic uncertainty quantification with low overhead. Using an extensive benchmark, we assess the reliability of verbalized confidence scores with respect to different datasets, models, and prompt methods. Our results reveal that the reliability of these scores strongly depends on how the model is asked, but also that it is possible to extract well-calibrated confidence scores with certain prompt methods. We argue that verbalized confidence scores can become a simple but effective and versatile uncertainty quantification method in the future. Our code is available at https://github.com/danielyxyang/llm-verbalized-uq.

Key facts. Cited by 83 papers in the map (data through 7 Oct 2026). Builds on 35 of its 48 references that are in the map. First posted on arXiv 19 Dec 2024.

Builds on

35 of 48 references.

References · 35

  1. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  2. 2017On Calibration of Modern Neural Networkscited by 4,860
  3. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  4. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  5. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  6. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  7. 2024Mixtral of Expertscited by 1,785
  8. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  9. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  10. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 946
  11. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  12. 2024Gemma: Open Models Based on Gemini Research and Technologycited by 889
23 more
  1. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 795
  2. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 788
  3. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  4. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 751
  5. 2017Crowdsourcing Multiple Choice Science Questionscited by 742
  6. 2022Teaching Models to Express Their Uncertainty in Wordscited by 731
  7. 2023Automatic Prompt Optimization with "Gradient Descent" and Beam Searchcited by 628
  8. 2023The Falcon Series of Open Language Modelscited by 526
  9. 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 439
  10. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 286
  11. 2022Prompting GPT-3 To Be Reliablecited by 258
  12. 2023FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarioscited by 247
  13. 2020Reducing conversational agents' overconfidence through linguistic calibrationcited by 209
  14. 2023Is Self-Repair a Silver Bullet for Code Generation?cited by 191
  15. 2024Benchmarking LLMs via Uncertainty Quantificationcited by 124
  16. 2023Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthinesscited by 121
  17. 2023Navigating the Grey Area: How Expressions of Uncertainty and Overconfidence Affect Language Modelscited by 91
  18. 2023Smooth ECE: Principled Reliability Diagrams via Kernel Smoothingcited by 59
  19. 2023What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variabilitycited by 51
  20. 2024Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Modelscited by 47
  21. 2023Quantifying Uncertainty in Natural Language Explanations of Large Language Modelscited by 31
  22. 2024Efficient Non-Parametric Uncertainty Quantification for Black-Box Large Language Models and Decision Planningcited by 16
  23. 2024On Subjective Uncertainty Quantification and Calibration in Natural Language Generationcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 30; 2026: 53.

83 papers.

Sort:

By area:

  1. 2025Maximizing Confidence Alone Improves Reasoningcited by 97
  2. 2025Reasoning Models Better Express Their Confidencecited by 63
  3. 2026How do LLMs Compute Verbal Confidencecited by 23
  4. 2025Enhancing Multi-Agent Debate System Performance via Confidence Expressioncited by 18
  5. 2025Lost in Transcription, Found in Distribution Shift: Demystifying Hallucination in Speech Foundation Modelscited by 17
  6. 2025Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Modelscited by 16
  7. 2025Rethinking the Reliability of Multi-agent System: A Perspective from Byzantine Fault Tolerancecited by 16
  8. 2025Extracting Probabilistic Knowledge from Large Language Models for Bayesian Network Parameterizationcited by 15
  9. 2025MetaFaith: Faithful Natural Language Uncertainty Expression in LLMscited by 15
  10. 2026Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunitiescited by 15
  11. 2025Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missingcited by 14
  12. 2025Uncertainty Distillation: Teaching Language Models to Express Semantic Confidencecited by 13
38 more
  1. 2026Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewardscited by 13
  2. 2025Thinking Out Loud: Do Reasoning Models Know When They're Right?cited by 12
  3. 2025Read Your Own Mind: Reasoning Helps Surface Self-Confidence Signals in LLMscited by 10
  4. 2025iMAD: Intelligent Multi-Agent Debate for Efficient and Accurate LLM Inferencecited by 10
  5. 2025Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systemscited by 8
  6. 2025ADVICE: Answer-Dependent Verbalized Confidence Estimationcited by 8
  7. 2025Teaching Language Models to Faithfully Express their Uncertaintycited by 7
  8. 2025Black-box Optimization of LLM Outputs by Asking for Directionscited by 7
  9. 2025On the Provable Performance Guarantee of Efficient Reasoning Modelscited by 6
  10. 2026Reaching Beyond the Mode: RL for Distributional Reasoning in Language Modelscited by 6
  11. 2026LLMs Should Express Uncertainty Explicitlycited by 6
  12. 2026From Debate to Decision: Conformal Social Choice for Safe Multi-Agent Deliberationcited by 6
  13. 2026Same Answer, Different Confidence: Protocol Sensitivity in LLM Confidence Calibrationcited by 6
  14. 2025BrowseConf: Confidence-Guided Test-Time Scaling for Web Agentscited by 5
  15. 2026NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG Systemscited by 5
  16. 2026Seven simple steps for log analysis in AI systemscited by 5
  17. 2026LLM Performance Predictors: Learning When to Escalate in Hybrid Human-AI Moderation Systemscited by 4
  18. 2026Influential Training Data Retrieval for Explaining Verbalized Confidence of LLMscited by 4
  19. 2026Calibration-Aware Policy Optimization for Reasoning LLMscited by 4
  20. 2026Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMscited by 4
  21. 2025Self-Reported Confidence of Large Language Models in Gastroenterology: Analysis of Commercial, Open-Source, and Quantized Modelscited by 3
  22. 2025Evaluating Uncertainty Quantification Methods in Argumentative Large Language Modelscited by 3
  23. 2025Let the Model Distribute Its Doubt: Confidence Estimation through Verbalized Probability Distributioncited by 3
  24. 2026Real-Time Trustworthiness Scoring for LLM Structured Outputs and Data Extractioncited by 3
  25. 2026SciPredict: Can LLMs Predict the Outcomes of Scientific Experiments in Natural Sciences?cited by 3
  26. 2026Scaling with Confidence: Calibrating Confidence of LLMs for Adaptive Test Time Scalingcited by 3
  27. 2025REHEARSE: Experiential Rehearsal for Verbal Confidence Calibration in Large Language Modelscited by 2
  28. 2025Trustworthy Agents for Electronic Health Records through Confidence Estimationcited by 2
  29. 2025Can Confidence Estimates Decide When Chain-of-Thought Is Necessary for LLMs?cited by 2
  30. 2026LLMs Know When They Know, but Do Not Act on It: A Metacognitive Harness for Test-time Scalingcited by 2
  31. 2026Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence?cited by 2
  32. 2026Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Predictioncited by 2
  33. 2026ConfidenceBench: Evaluating Confidence Calibration in Large Language Modelscited by 2
  34. 2025Dist2ill: Distributional Distillation for One-Pass Uncertainty Estimation in Large Language Modelscited by 1
  35. 2025ConfProBench: A Confidence Evaluation Benchmark for MLLM-Based Process Judgescited by 1
  36. 2025GuessingGame: Measuring the Informativeness of Open-Ended Questions in Large Language Modelscited by 1
  37. 2025Token-Level Marginalization for Multi-Label LLM Classifierscited by 1
  38. 2026Unlocking the Pre-Trained Model as a Dual-Alignment Calibrator for Post-Trained LLMscited by 1

50 most cited of 83 All 83 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey
  2. 2024Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models
  3. 2024Cycles of Thought: Measuring LLM Confidence through Stable Explanations
  4. 2026Rethinking Uncertainty Evaluation in Large Language Models
  5. 2026Rethinking Verbalized Confidence for LLM-as-a-Judge: A Compatibility Shift on Post-2025 Proprietary Models
  6. 2026Not All Uncertainty Is Equal: How Uncertainty Granularity Shapes Human Verification in LLM-Assisted Decision Making ↗
  7. 2024Confidence in the Reasoning of Large Language Models
  8. 2026Claim-Level Confidence Calibration for Reliable Decision Making with Large Language Models