mlsanityData to 14 Oct 2026

CritiCal: Can Critique Help LLM Uncertainty or Confidence Calibration?

arXiv 2510.24505 ↗First posted 28 Oct 2025cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

Accurate confidence calibration in Large Language Models (LLMs) is critical for safe use in high-stakes domains, where clear verbalized confidence enhances user trust. Traditional methods that mimic reference confidence expressions often fail to capture the reasoning needed for accurate confidence assessment. We propose natural language critiques as a solution, ideally suited for confidence calibration, as precise gold confidence labels are hard to obtain and often require multiple generations. This paper studies how natural language critiques can enhance verbalized confidence, addressing: (1) What to critique: uncertainty (question-focused) or confidence (answer-specific)? Analysis shows confidence suits multiple-choice tasks, while uncertainty excels in open-ended scenarios. (2) How to critique: self-critique or critique calibration training? We propose Self-Critique, enabling LLMs to critique and optimize their confidence beyond mere accuracy, and CritiCal, a novel Critique Calibration training method that leverages natural language critiques to improve confidence calibration, moving beyond direct numerical optimization. Experiments show that CritiCal significantly outperforms Self-Critique and other competitive baselines, even surpassing its teacher model, GPT-4o, in complex reasoning tasks. CritiCal also shows robust generalization in out-of-distribution settings, advancing LLM's reliability.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 34 of its 46 references that are in the map. First posted on arXiv 28 Oct 2025.

Builds on

34 of 46 references.

References · 34

  1. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  2. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  3. 2023Let's Verify Step by Stepcited by 3,789
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  5. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  6. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  7. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,302
  8. 2024Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvementcited by 1,090
  9. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  10. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 974
  11. 2023Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotationscited by 928
  12. 2023Large Language Modelscited by 780
22 more
  1. 2022Teaching Models to Express Their Uncertainty in Wordscited by 751
  2. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  3. 2023The Internal State of an LLM Knows When It's Lyingcited by 659
  4. 2022Generating Sequences by Learning to Self-Correctcited by 277
  5. 2025Beyond Binary Rewards: Training LMs to Reason About Their Uncertaintycited by 117
  6. 2023Can Large Language Models Really Improve by Self-critiquing Their Own Plans?cited by 108
  7. 2024SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationalescited by 105
  8. 2025From Automation to Autonomy: A Survey on Large Language Models in Scientific Discoverycited by 93
  9. 2025Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedbackcited by 90
  10. 2025MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbationscited by 89
  11. 2025Efficient Test-Time Scaling via Self-Calibrationcited by 75
  12. 2024API Is Enough: Conformal Prediction for Large Language Models Without Logit-Accesscited by 69
  13. 2024ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guaranteescited by 65
  14. 2025Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitatecited by 63
  15. 2025A Survey of Uncertainty Estimation Methods on Large Language Modelscited by 62
  16. 2025ConfTuner: Training Large Language Models to Express Their Confidence Verballycited by 39
  17. 2025NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agentscited by 36
  18. 2025The Curse of CoT: On the Limitations of Chain-of-Thought in In-Context Learningcited by 30
  19. 2024Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMscited by 29
  20. 2025Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?cited by 16
  21. 2024ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertaintycited by 10
  22. 2025Rethinking Prospect Theory for LLMs: Revealing the Instability of Decision-Making under Epistemic Uncertaintycited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystemscited by 11
  2. 2026Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistencycited by 2
  3. 2026EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary Worldcited by 1
  4. 2026MultivationBench: A Benchmark for Multimodal Sequential Motivation Reasoningcited by 1