13 citations · 19 across the 10 of their papers we have counts for
3 papers · 1 filter
Evaluating and Explaining Prompt Sensitivity of LLMs Using Interactions
Ruiyang Qin, Qingzhuo Wang, Tian Wang +2
The remarkable capabilities of large language models (LLMs) are often undermined by their instability. Even subtle and semantically irrelevant changes in prompts can cause dramatic…
A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions
Qingzhuo Wang, Ruiyang Qin, Zhenxin Qin +2
Despite the success of knowledge distillation (KD) in Large Language Models (LLMs), the underlying mechanism behind its efficacy remains unclear. In this paper, we propose a unifie…
Multilingual Safety Alignment via Self-Distillation
Ruiyang Qin, Qingzhuo Wang, Dongrui Liu +3
Large language models (LLMs) exhibit severe multilingual safety misalignment: they possess strong safeguards in high-resource languages but remain highly vulnerable to jailbreak at…