2 papers
cs.CR2026
SafeThinker: Reasoning about Risk to Deepen Safety Beyond Shallow Alignment
Xianya Fang, Xianying Luo, Yadong Wang +8
Despite the intrinsic risk-awareness of Large Language Models (LLMs), current defenses often result in shallow safety alignment, rendering models vulnerable to disguised attacks (e…
cs.LG2026
Beyond Superficial Unlearning: Sharpness-Aware Robust Erasure of Hallucinations in Multimodal LLMs
Xianya Fang, Feiyang Ren, Xiang Chen +4
Multimodal LLMs are powerful but prone to object hallucinations, which describe non-existent entities and harm reliability. While recent unlearning methods attempt to mitigate this…