paper-with-me

Papers

Can Confidence Estimates Decide When Chain-of-Thought Is Necessary for LLMs?

2025-10-23 · Samuel Lewis-Lim, Xingwei Tan, Zhixue Zhao, Nikolaos Aletras arxiv

Chain-of-thought (CoT) prompting is a common technique for improving the reasoning abilities of large language models (LLMs). However, extended reasoning is often unnecessary and substantially increases token usage. As such, a key question becomes how to optimally allocate compute to when reasoning is actually needed. We study this through confidence-gated CoT, where a model produces a direct answer and a confidence estimate to decide whether to invoke CoT. We present an evaluation framework together with the first systematic study of confidence signals for this decision. We evaluate four representative confidence measures and compare them with random gating and an oracle upper bound. Experiments across two model families and diverse reasoning tasks show that existing training-free confidence measures can reduce redundant reasoning. However, we also find that the utility of individual confidence measures is inconsistent across settings. Through our evaluation framework and analysis, our study provides practical guidance toward developing and evaluating models that selectively use CoT.

📄 PDF Abstract BibTeX arXiv:2510.21007

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Therefore I am. I Think

2026-04-01 · Esakkivel Esakkiraja, Sai Rajeswar, Denis Akhiyarov, Rajagopal Venkatesaramani arxiv

We consider the question: when a large language reasoning model makes a choice, did it think first and then decide to, or decide first and then think? In this paper, we present evidence that detectable, early-encoded dec…

Temporalizing Confidence: Evaluation of Chain-of-Thought Reasoning with Signal Temporal Logic

2025-06-09 · Zhenjiang Mao, Artem Bisliouk, Rohith Reddy Nama, Ivan Ruchkin

Large Language Models (LLMs) have shown impressive performance in mathematical reasoning tasks when guided by Chain-of-Thought (CoT) prompting. However, they tend to produce highly confident yet incorrect outputs, which …

Mathematical Reasoning

Early Stopping for Large Reasoning Models via Confidence Dynamics

2026-04-06 · Parsa Hosseini, Sumit Nawathe, Mahdi Salmani, Meisam Razaviyayn 외 arxiv

Large reasoning models rely on long chain-of-thought generation to solve complex problems, but extended reasoning often incurs substantial computational cost and can even degrade performance due to overthinking. A key ch…

Optimizing Chain-of-Thought Confidence via Topological and Dirichlet Risk Analysis

2025-11-09 · Abhishek More, Anthony Zhang, Nicole Bonilla, Ashvik Vivekan 외 arxiv

Chain-of-thought (CoT) prompting enables Large Language Models to solve complex problems, but deploying these models safely requires reliable confidence estimates, a capability where existing methods suffer from poor cal…

Stock Price Prediction

The Cost of Reasoning: Chain-of-Thought Induces Overconfidence in Vision-Language Models

2026-03-17 · Robert Welch, Emir Konuk, Kevin Smith arxiv

Vision-language models (VLMs) are increasingly deployed in high-stakes settings where reliable uncertainty quantification (UQ) is as important as predictive accuracy. Extended reasoning via chain-of-thought (CoT) prompti…