الباحثون

Yufan Zhou

المنشورات 2

نسخة أولية وصول مفتوح

How Far Do Persona Effects Generalize in Language Models?

Yufan Zhou, Yuxuan Liu, Enze Ma وآخرون · 2026

Persona prompts ask language models to answer as particular kinds of people. We test whether relationships learned from these effects predict responses to new questions and remain useful across models and prompts. Across 57 attributes, three behavioral domains, and seven pairs of open 7 to 9B checkpoints, persona effec …

نسخة أولية وصول مفتوح

Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States

Zixuan Wang, Yufan Zhou, Jinzhou Tang وآخرون · 2026

As language models become more capable, long-term collaboration in learning, reasoning, and decision-making calls for a deeper understanding of the people they serve. Yet training such human-aware language models faces a fundamental supervision gap because current datasets for LLM assistant training contain few if any …

المؤلفون المشاركون