2 papers
cs.LG2025
OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment
Liang Lin, Zhihao Xu, Junhao Dong +10
Large language model (LLM) alignment faces a critical dilemma when addressing multiple human preferences: improvements in one dimension frequently come at the expense of others, cr…
cs.CL2025
Paper Summary Attack: Jailbreaking LLMs through LLM Safety Papers
Liang Lin, Zhihao Xu, Xuehai Tang +5
The safety of large language models (LLMs) has garnered significant research attention. In this paper, we argue that previous empirical studies demonstrate LLMs exhibit a propensit…