Jianxun Lian

Learning to summarize user information for personalized reinforcement learning from human feedback

Social-R1: Enhancing Social Intelligence in LLMs through Human-like Reinforced Reasoning

To Think or Not To Think, That is The Question for LLM Reasoning in Theory of Mind Tasks

Eliciting Human-like Social Reasoning in Large Language Models

From Assistants to Companions: Towards the Usefulness of Improving Theory of Mind for Human-AI Symbiosis

Personalized Safety in LLMs: A Benchmark and A Planning-Based Agent Approach

Unveiling the Learning Mind of Language Models: A Cognitive Framework and Empirical Study