3 accepted papers
Safety-aligned large language models (LLMs) are becoming increasingly widespread, especially in sensitive applications where fairness is essential and biased outputs can cause significant harm. However, evaluating the fairness of models is a complex challenge, and approaches that do so typically uti
Safety-aligned LLMs respond to prompts with either compliance or refusal, each corresponding to distinct directions in the model’s activation space. Recent studies have shown that initializing attacks via self-transfer from other prompts significantly enhances their performance. However, the underly
Existing Graph Neural Networks (GNNs) compute the message exchange between nodes by either aggregating uniformly (convolving) the features of all the neighbor- ing nodes, or by applying a non-uniform score (attending) to the features. Recent works have shown the strengths and weaknesses of the resul…