Uncertainty Under the Curve: A Sequence-Level Entropy Area Metric for Reasoning LLM

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Yongfu, Sun, Lin, Zhao, Guangxiang, Lin, Weihong, Zhang, Xiangzheng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911127481352192
author Zhu, Yongfu
Sun, Lin
Zhao, Guangxiang
Lin, Weihong
Zhang, Xiangzheng
author_facet Zhu, Yongfu
Sun, Lin
Zhao, Guangxiang
Lin, Weihong
Zhang, Xiangzheng
contents In this work, we introduce Entropy Area Score (EAS), a simple yet effective metric to quantify uncertainty in the answer generation process of reasoning large language models (LLMs). EAS requires neither external models nor repeated sampling, it integrates token-level predictive entropy from the model itself to capture the evolution of uncertainty during generation. Empirical results show that EAS is strongly correlated with answer entropy across models and datasets. In training data selection, EAS identifies high-potential samples and consistently outperforms Pass Rate filtering under equal sample budgets, improving student model accuracy on math benchmarks. EAS is both efficient and interpretable, offering a practical tool for uncertainty modeling and data quality assessment in LLM training.
format Preprint
id arxiv_https___arxiv_org_abs_2508_20384
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Uncertainty Under the Curve: A Sequence-Level Entropy Area Metric for Reasoning LLM
Zhu, Yongfu
Sun, Lin
Zhao, Guangxiang
Lin, Weihong
Zhang, Xiangzheng
Artificial Intelligence
In this work, we introduce Entropy Area Score (EAS), a simple yet effective metric to quantify uncertainty in the answer generation process of reasoning large language models (LLMs). EAS requires neither external models nor repeated sampling, it integrates token-level predictive entropy from the model itself to capture the evolution of uncertainty during generation. Empirical results show that EAS is strongly correlated with answer entropy across models and datasets. In training data selection, EAS identifies high-potential samples and consistently outperforms Pass Rate filtering under equal sample budgets, improving student model accuracy on math benchmarks. EAS is both efficient and interpretable, offering a practical tool for uncertainty modeling and data quality assessment in LLM training.
title Uncertainty Under the Curve: A Sequence-Level Entropy Area Metric for Reasoning LLM
topic Artificial Intelligence
url https://arxiv.org/abs/2508.20384