3 papers
cs.CR2026
One Skill, Two Masters: Serving Users and Attackers through Skill Injection
Haochang Hao, Dehai Min, Zhifang Zhang +5
Large language model agents use skills that package reusable instructions, code, and resources. Existing skill-injection attacks exploit trust in these packages by adding malicious…
cs.CL2026
Beyond Math and Code: Lightweight Corpus-Grounded Process Rewards for Factual Question Answering
Shicheng Fan, Haochang Hao, Dehai Min +10
Process supervision during reinforcement learning (RL) post-training matters in factual question answering (QA) because responses receiving positive response-level rewards can stil…
cs.CL2026
SafeCRS: Personalized Safety Alignment for LLM-Based Conversational Recommender Systems
Haochang Hao, Yifan Xu, Xinzhuo Li +2
Current LLM-based conversational recommender systems (CRS) primarily optimize recommendation accuracy and user satisfaction. We identify an underexplored vulnerability in which rec…