Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
When Does a Language Model Commit? A Finite-Answer Theory of Pre-Verbalization Commitment
Long Zhang, Wei-neng Chen, Feng-feng Wei +1
Language models often generate reasoning before giving a final answer, but the visible answer does not reveal when the model's answer preference became stable. We study this questi…
cs.AI2026
Authority Inversion in LLM-Mediated Ubiquitous Systems: When Models Trust Users Over Sensors
Long Zhang, Zi-bo Qin, Wei-neng Chen
Large language models (LLMs) increasingly fuse heterogeneous inputs in ubiquitous systems. Yet, how LLMs implicitly allocate authority when sensor measurements and user claims conf…