Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Suppressing Pressure, Amplifying Evidence: Self-Guided Attention Steering to Mitigate Sycophancy and Stubbornness
Yinghao He, Mengyu Xu, Haixiang Sun +8
Reliable language models should resist unsupported user pressure while effectively using objective contextual information. However, models may exhibit sycophancy by yielding to uns…
cs.AI2026
Positive-Unlabeled Learning for Agent Safety False Alarm Auditing
Xichen Yan, Chongyang Gao, Kezhen Chen +3
Safety monitors help safeguard language-model agents interacting with external tools and environments, but conservative monitoring can generate many false alarms, consuming extensi…