Sijun Tan

Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test

Budget-aware Test-time Scaling via Discriminative Verification

DeepScaleR: Effective RL Scaling of Reasoning Models via Iterative Context Lengthening

TherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy Chatbots

JudgeBench: A Benchmark for Evaluating LLM-Based Judges