Jiarui Liu

CauSciBench: A Comprehensive Benchmark on End-to-End Causal Inference for Scientific Research

LLM Microscope: What Model Internals Reveal About Answer Correctness and Context Utilization

Social World Models: Universal Structured Representations for Social Reasoning

Stabilizing Reinforcement Learning for Honesty Alignment in Language Models on Deductive Reasoning

Language Model Alignment in Multilingual Trolley Problems

BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data