Bing Liu

Online Rubrics Elicitation from Pairwise Comparisons

MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes

Chasing the Tail: Effective Rubric-based Reward Modeling for Large Language Model Post-Training

ResearchRubrics: A Benchmark of Prompts and Rubrics For Evaluating Deep Research Agents

Beyond Seeing: Evaluating Multimodal LLMs on Tool-Enabled Image Perception, Transformation, and Reasoning

SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains

TutorBench: A Benchmark To Assess Tutoring Capabilities Of Large Language Models

Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models