Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
When In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference Shift
Khoi Le, Tri Cao, Phong Nguyen +5
Weak-to-strong (W2S) generalization is a promising framework for scalable oversight, yet existing evaluations often test students under matched train-test distributions. Therefore,…
cs.CL2025
Automating Steering for Safe Multimodal Large Language Models
Lyucheng Wu, Mengru Wang, Ziwen Xu +4
Recent progress in Multimodal Large Language Models (MLLMs) has unlocked powerful cross-modal reasoning abilities, but also raised new safety concerns, particularly when faced with…