Exploiting Instruction-Following Retrievers for Malicious Information Retrieval Paper • 2503.08644 • Published 2 days ago • 15
SafeArena: Evaluating the Safety of Autonomous Web Agents Paper • 2503.04957 • Published 7 days ago • 18
Societal Alignment Frameworks Can Improve LLM Alignment Paper • 2503.00069 • Published 14 days ago • 16