SyncAI.news, a Varaisys broadcasting
When Words Fall Short: Iterative Synergy Between Verbalized Reasoning and Hidden Features for LLM Confidence Estimation
YX

Yekun Xu, Ante Wang, Jingyi Ren, Xuanyi Chen, Weizhi Ma, Yang Liu

· 1 min read

ResearcharXiv cs.CL

When Words Fall Short: Iterative Synergy Between Verbalized Reasoning and Hidden Features for LLM Confidence Estimation

arXiv:2609.34454v1 Announce Type: new Abstract: Confidence estimation is crucial for developing trustworthy large language models (LLMs), with most methods following estimator-based or verbalization-based paradigms. While recent research increasingly focuses on improving verbalized self-reports of confidence, we challenge the prevailing view that this approach surpasses independent confidence estimators. Our empirical study shows that a dedicated confidence estimator can substantially outperform verbalized confidence, indicating that LLMs' internal representations contain richer confidence signals. Building on this finding, we propose Iterative Policy-Estimator Training (IPoET), a framework that synergizes the complementary strengths of verbalized reasoning traces and informative representations. IPoET alternates policy optimization with estimator updating, integrating estimator-derived confidence feedback into policy learning and refreshing the estimator on new policy rollouts. Experiments across diverse datasets and Qwen and Llama backbones demonstrate that, by iteratively exploiting richer hidden features and adapting to the evolving policy distribution, IPoET consistently outperforms both estimator- and verbalization-based baselines in-domain and achieves superior or comparable results across all out-of-domain metrics. For more details, refer to https://github.com/xyk829/ipoet.

Original source

This story was published by arXiv cs.CL and written by Yekun Xu, Ante Wang, Jingyi Ren, Xuanyi Chen, Weizhi Ma, Yang Liu. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News