一作ACL 2026Poster· Natural Language Processing
ADVICE : Answer-Dependent Verbalized Confidence Estimation
KiJung Seo · Sehun Lim · Taeuk Kim
摘要
Recent progress in large language models (LLMs) has enabled them to communicate their confidence in natural language, improving transparency and reliability.However, this expressiveness is often accompanied by systematic overconfidence, whose underlying causes remain poorly understood. In this wo...