一作ACL 2026Poster· Natural Language Processing
Learning Uncertainty from Sequential Internal Dispersion in Large Language Models
Ponhvoan Srey · Xiaobao Wu · Cong-Duy T Nguyen · Anh Tuan Luu
摘要
Uncertainty estimation is a promising approach to detect hallucinations in large language models (LLMs). Recent approaches commonly depend on model internal states to estimate uncertainty. However, they suffer from strict assumptions on how hidden states should evolve across layers, and from info...