Showing 2026Show all
2 papers · 1 filter
cs.CL2026
Modeling the Arrival Time of Information-Bearing Events in Natural Language
Leyi Lao, Yulin Ou, Yang Xu +1
Understanding how information is distributed over time is fundamental to modeling natural language. While existing empirical studies primarily rely on post-hoc analysis of informat…
cs.CL2026
Purging the Gray Zone: Latent-Geometric Denoising for Precise Knowledge Boundary Awareness
Hao An, Yibin Lou, Jiayi Guo +1
Large language models (LLMs) often exhibit hallucinations due to their inability to accurately perceive their own knowledge boundaries. Existing abstention fine-tuning methods typi…