2 papers
cs.AI2026
LLM Detoxification via Transition-Aware Reward-Guided Representation Sampling
Aishan Liu, Yisong Xiao, Xianglong Liu +7
Large Language Models (LLMs) can generate toxic content, motivating effective test-time detoxification. Existing representation steering methods often rely on static or coarse inte…
cs.CL2026
Mitigating Bias in Large Vision-Language Models via Counterfactual Ensemble Decoding
Yisong Xiao, Aishan Liu, Yongxin Huang +6
Large Vision-Language Models (LVLMs) have achieved remarkable performance across a wide range of tasks; however, they often inherit social biases from their training data, resultin…