Enhancing Uncertainty Estimation in LLMs with Expectation of Aggregated Internal Belief

Zeguan Xiao; Diyang Dou; Boya Xiong; Yun Chen; Guanhua Chen

AAAI 2026technical0 citations

Enhancing Uncertainty Estimation in LLMs with Expectation of Aggregated Internal Belief

Zeguan Xiao, Diyang Dou, Boya Xiong, Yun Chen, Guanhua Chen

Abstract

Large Language Models (LLMs) have achieved remarkable success across a wide range of natural language tasks, but often exhibit overconfidence and generate plausible yet incorrect answers. This overconfidence, especially in models undergone Reinforcement Learning from Human Feedback (RLHF), poses significant challenges for reliable uncertainty estimation and safe deployment. In this paper, we propose EAGLE (Expectation of AGgregated internaL bEief), a novel self-evaluation-based calibration method that leverages the internal hidden states of LLMs to derive more accurate confidence scores. Instead of relying on the model

BibTeX

@inproceedings{aaai2026_enhancinguncerta,
  title = {Enhancing Uncertainty Estimation in LLMs with Expectation of Aggregated Internal Belief},
  author = {Zeguan Xiao and Diyang Dou and Boya Xiong and Yun Chen and Guanhua Chen},
  booktitle = {AAAI 2026},
  year = {2026}
}