3 papers
cs.CL2026
Alignment by Stereotyping: How LLMs Sacrifice Individual Distinctiveness for Cultural Adaptation
Qishuai Zhong, Zongmin Li, Siqi Fan +1
Large language models are increasingly deployed for personalized interaction, and demographic conditioning via user profiles is a widely adopted strategy for cultural adaptation. W…
cs.LG2026
Can LLM Safety Be Ensured by Constraining Parameter Regions?
Zongmin Li, Jian Su, Farah Benamara +1
Large language models (LLMs) are often assumed to contain ``safety regions'' -- parameter subsets whose modification directly influences safety behaviors. We conduct a systematic e…
cs.CL2025
Evaluating LLM Adaptation to Sociodemographic Factors: User Profile vs. Dialogue History
Qishuai Zhong, Zongmin Li, Siqi Fan +1
Effective engagement by large language models (LLMs) requires adapting responses to users' sociodemographic characteristics, such as age, occupation, and education level. While man…