Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration 事件

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration arXiv:2606.05396v1 Announce Type: cross Abstract: Producing a labeled vulnerable code at scale is a recurring obstacle for learning-based vulnerability detection: mined corpora carry substantial label noise, and existing LLM-based augmentation propagates these inaccuracies because it transforms vulnerable seeds rather than synthesising vulnerabilities from a specification. A complementary route is to start from