Reasoning Models Better Express Their Confidence

• URL: http://arxiv.org/abs/2505.14489v1
• Date: Tue, 20 May 2025 15:19:00 GMT
• Title: Reasoning Models Better Express Their Confidence
• Authors: Dongkeun Yoon, Seungone Kim, Sohee Yang, Sunkyoung Kim, Soyeon Kim, Yongil Kim, Eunbi Choi, Yireun Kim, Minjoon Seo,
• Abstract summary: Large language models (LLMs) often fail to communicate their confidence accurately, making it difficult to assess when they might be wrong and limiting their reliability.<n>In this work, we demonstrate that reasoning models-LLMs that engage in extended chain-of-thought (CoT) reasoning-exhibit superior performance not only in problem-solving but also in accurately expressing their confidence.
• Score: 33.72935464539185
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite their strengths, large language models (LLMs) often fail to communicate their confidence accurately, making it difficult to assess when they might be wrong and limiting their reliability. In this work, we demonstrate that reasoning models-LLMs that engage in extended chain-of-thought (CoT) reasoning-exhibit superior performance not only in problem-solving but also in accurately expressing their confidence. Specifically, we benchmark six reasoning models across six datasets and find that they achieve strictly better confidence calibration than their non-reasoning counterparts in 33 out of the 36 settings. Our detailed analysis reveals that these gains in calibration stem from the slow thinking behaviors of reasoning models-such as exploring alternative approaches and backtracking-which enable them to adjust their confidence dynamically throughout their CoT, making it progressively more accurate. In particular, we find that reasoning models become increasingly better calibrated as their CoT unfolds, a trend not observed in non-reasoning models. Moreover, removing slow thinking behaviors from the CoT leads to a significant drop in calibration. Lastly, we show that these gains are not exclusive to reasoning models-non-reasoning models also benefit when guided to perform slow thinking via in-context learning.

Related papers

• Inverse Scaling in Test-Time Compute [51.16323216811257]
  Extending the reasoning length of Large Reasoning Models (LRMs) deteriorates performance.<n>We identify five distinct failure modes when models reason for longer.<n>These findings suggest that while test-time compute scaling remains promising for improving model capabilities, it may inadvertently reinforce problematic reasoning patterns.
  arXiv  Detail & Related papers  (2025-07-19T00:06:13Z)
• Large Reasoning Models are not thinking straight: on the unreliability of thinking trajectories [0.0]
  Large Language Models (LLMs) trained via Reinforcement Learning (RL) have recently achieved impressive results on reasoning benchmarks.<n>Yet, growing evidence shows that these models often generate longer but ineffective chains of thought (CoTs)<n>We present new evidence of overthinking, where models disregard correct solutions even when explicitly provided, instead continuing to generate unnecessary reasoning steps.
  arXiv  Detail & Related papers  (2025-07-01T12:14:22Z)
• Lost at the Beginning of Reasoning [82.18834329384514]
  We show that the first reasoning step exerts a disproportionately large influence on the final prediction.<n>We propose an efficient sampling strategy that leverages a reward model to identify and retain high-quality first reasoning steps.<n>We introduce a new benchmark specifically constructed with deliberately flawed first reasoning steps to systematically evaluate model self-correction capabilities.
  arXiv  Detail & Related papers  (2025-06-27T09:53:57Z)
• Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know? [7.423494663010787]
  Reasoning language models have set state-of-the-art (SOTA) records on many challenging benchmarks.<n>Like previous language models, reasoning models are prone to generating confident, plausible responses that are incorrect.<n>Knowing when and how much to trust these models is critical to the safe deployment of reasoning models in real-world applications.
  arXiv  Detail & Related papers  (2025-06-22T21:46:42Z)
• Does Thinking More always Help? Understanding Test-Time Scaling in Reasoning Models [103.03315678501546]
  Extending thinking traces using prompts like "Wait" or "Let me rethink" can improve performance.<n>This raises a natural question: Does thinking more at test-time truly lead to better reasoning?<n>We show a consistent pattern of initial performance improvements from additional thinking followed by a decline, due to "overthinking"
  arXiv  Detail & Related papers  (2025-06-04T17:55:09Z)
• Verbalized Confidence Triggers Self-Verification: Emergent Behavior Without Explicit Reasoning Supervision [12.287123198288079]
  Uncertainty calibration is essential for the safe deployment of large language models (LLMs)<n>We find that supervised fine-tuning with scalar confidence labels alone suffices to elicit self-verification behavior of language models.<n>We propose a simple rethinking method that boosts performance via test-time scaling based on calibrated uncertainty.
  arXiv  Detail & Related papers  (2025-06-04T08:56:24Z)
• CoThink: Token-Efficient Reasoning via Instruct Models Guiding Reasoning Models [56.40065909544213]
  Large language models (LLMs) benefit from increased test-time compute, a phenomenon known as test-time scaling.<n>However, reasoning-optimized models often overthink even simple problems, producing excessively verbose outputs and leading to low token efficiency.<n>We identify two key causes of this verbosity: (1) reinforcement learning reduces the information density of forward reasoning, and (2) backward chain-of thought training encourages redundant and often unnecessary verification steps.
  arXiv  Detail & Related papers  (2025-05-28T06:24:45Z)
• Do Reasoning Models Show Better Verbalized Calibration? [19.776645881640178]
  We investigate the calibration properties of LRMs trained via supervised fine-tuning distillation on long reasoning traces.<n>Our findings reveal that LRMs significantly outperform instruction-tuned models on complex reasoning tasks in both accuracy and confidence calibration.<n>Our results provide evidence for a potentially critical role of reasoning-oriented RL training in improving LLMs' capacity for generating trustworthy, self-aware outputs.
  arXiv  Detail & Related papers  (2025-04-09T03:58:19Z)
• Calibrating LLM Confidence with Semantic Steering: A Multi-Prompt Aggregation Framework [11.872504642312705]
  Large Language Models (LLMs) often exhibit misaligned confidence scores, usually overestimating the reliability of their predictions.<n>We propose a novel framework containing three components: confidence steering, steered confidence aggregation and steered answers selection.<n>We evaluate our method on 7 benchmarks and it consistently outperforms the baselines in terms of calibration metrics in task of confidence calibration and failure detection.
  arXiv  Detail & Related papers  (2025-03-04T18:40:49Z)
• Enhancing LLM Reliability via Explicit Knowledge Boundary Modeling [48.15636223774418]
  Large language models (LLMs) frequently hallucinate due to misaligned self-awareness.<n>Existing approaches mitigate hallucinations via uncertainty estimation or query rejection.<n>We propose the Explicit Knowledge Boundary Modeling framework to integrate fast and slow reasoning systems.
  arXiv  Detail & Related papers  (2025-03-04T03:16:02Z)
• Mind the Confidence Gap: Overconfidence, Calibration, and Distractor Effects in Large Language Models [0.6091702876917281]
  This paper examines how model size, mitigateors, and question types affect confidence alignment.<n>We introduce an evaluation framework to measure overconfidence and investigate whether multiple-choice formats or worsen miscalibration.
  arXiv  Detail & Related papers  (2025-02-16T07:46:09Z)
• Calibrating Large Language Models with Sample Consistency [76.23956851098598]
  We explore the potential of deriving confidence from the distribution of multiple randomly sampled model generations, via three measures of consistency. Results show that consistency-based calibration methods outperform existing post-hoc approaches. We offer practical guidance on choosing suitable consistency metrics for calibration, tailored to the characteristics of various LMs.
  arXiv  Detail & Related papers  (2024-02-21T16:15:20Z)
• Selective Learning: Towards Robust Calibration with Dynamic Regularization [79.92633587914659]
  Miscalibration in deep learning refers to there is a discrepancy between the predicted confidence and performance. We introduce Dynamic Regularization (DReg) which aims to learn what should be learned during training thereby circumventing the confidence adjusting trade-off.
  arXiv  Detail & Related papers  (2024-02-13T11:25:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.