paper-with-me

홈 › Papers

Thought calibration: Efficient and confident test-time scaling

2025-05-23 · Menghua Wu, Cai Zhou, Stephen Bates, Tommi Jaakkola

Reasoning large language models achieve impressive test-time scaling by thinking for longer, but this performance gain comes at significant compute cost. Directly limiting test-time budget hurts overall performance, but not all problems are equally difficult. We propose thought calibration to decide dynamically when thinking can be terminated. To calibrate our decision rule, we view a language model's growing body of thoughts as a nested sequence of reasoning trees, where the goal is to identify the point at which novel reasoning plateaus. We realize this framework through lightweight probes that operate on top of the language model's hidden representations, which are informative of both the reasoning structure and overall consistency of response. Based on three reasoning language models and four datasets, thought calibration preserves model performance with up to a 60% reduction in thinking tokens on in-distribution data, and up to 20% in out-of-distribution data.

📄 PDF Abstract BibTeX arXiv:2505.18404

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Improving Calibration by Relating Focal Loss, Temperature Scaling, and Properness

2024-08-21 · Viacheslav Komisarenko, Meelis Kull

Proper losses such as cross-entropy incentivize classifiers to produce class probabilities that are well-calibrated on the training data. Due to the generalization gap, these classifiers tend to become overconfident on t…

image-classificationImage Classification

Domain-adaptive and Subgroup-specific Cascaded Temperature Regression for Out-of-distribution Calibration

2024-02-14 · Jiexin Wang, Jiahao Chen, Bing Su

Although deep neural networks yield high classification accuracy given sufficient training data, their predictions are typically overconfident or under-confident, i.e., the prediction confidences cannot truly reflect the…

Data Augmentationregression

Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning

2026-05-13 · Yu Gu, Zijun Yu, Vahid Partovi Nia, Masoud Asgharian arxiv

Chain-of-thought (CoT) reasoning with self-consistency improves performance by aggregating multiple sampled reasoning paths. In this setting, correctness is no longer tied to a single reasoning trace but to the aggregati…

Identifying Influential N-grams in Confidence Calibration via Regression Analysis

2026-04-07 · Shintaro Ozaki, Wataru Hashimoto, Hidetaka Kamigaito, Katsuhiko Hayashi 외 arxiv

While large language models (LLMs) improve performance by explicit reasoning, their responses are often overconfident, even though they include linguistic expressions demonstrating uncertainty. In this work, we identify …

Improving Confidence Estimates for Unfamiliar Examples

2018-04-09 · CVPR 2020 6 · Zhizhong Li, Derek Hoiem

Intuitively, unfamiliarity should lead to lack of confidence. In reality, current algorithms often make highly confident yet wrong predictions when faced with relevant but unfamiliar examples. A classifier we trained to …

AttributeDomain Adaptation