Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
HINTBench: Horizon-agent Intrinsic Non-attack Trajectory Benchmark
Jiacheng Wang, Jinchang Hou, Fabian Wang +3
Existing agent-safety evaluation has focused mainly on externally induced risks. Yet agents may still enter unsafe trajectories under benign conditions. We study this complementary…
cs.LG2026
Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis
Wang Cai, Yilin Wen, Jinchang Hou +5
Safety alignment in Large Language Models (LLMs) inherently presents a multi-objective optimization conflict, often accompanied by an unintended degradation of general capabilities…