作者位次 #2/4ACL 2026Findings· Findings of ACL
Purging the Gray Zone: Latent-Geometric Denoising for Precise Knowledge Boundary Awareness
Hao An · Yibin Lou · Jiayi Guo · Yang Xu
摘要
Large language models (LLMs) often exhibit hallucinations due to their inability to accurately perceive their own knowledge boundaries. Existing abstention fine-tuning methods typically partition datasets directly based on response accuracy, causing models to suffer from severe label noise near t...