13 papers
ChemVA: Advancing Large Language Models on Chemical Reaction Diagrams Understanding
Mingyang Rao, Kehua Feng, Zhihui Zhu +4
While Large Language Models (LLMs) have revolutionized scientific text processing, they exhibit a significant capability gap when interpreting chemical reaction diagrams. We identi…
Embodied Science: Closing the Discovery Loop with Agentic Embodied AI
Xiang Zhuang, Chenyi Zhou, Kehua Feng +10
Artificial intelligence has demonstrated remarkable capability in predicting scientific properties, yet scientific discovery remains an inherently physical, long-horizon pursuit go…
Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple LLM Judges
Yuqi Tang, Kehua Feng, Yunfeng Wang +6
Evaluating the conversational abilities of large language models (LLMs) remains a challenging task. Current mainstream approaches primarily rely on the "LLM-as-a-judge" paradigm, w…
Evaluating Reward Model Generalization via Pairwise Maximum Discrepancy Competitions
Shunyang Luo, Peibei Cao, Zhihui Zhu +3
Reward models (RMs) are central to aligning large language models, yet their practical effectiveness hinges on generalization to unseen prompts and shifting distributions. Most exi…
ClinDEF: A Dynamic Evaluation Framework for Large Language Models in Clinical Reasoning
Yuqi Tang, Jing Yu, Zichang Su +7
Clinical diagnosis begins with doctor-patient interaction, during which physicians iteratively gather information, determine examination and refine differential diagnosis through p…
CoT-Evo: Evolutionary Distillation of Chain-of-Thought for Scientific Reasoning
Kehua Feng, Keyan Ding, Zhihui Zhu +3
While chain-of-thought (CoT) distillation from advanced large language models (LLMs) has proven effective in general reasoning tasks, it struggles in scientific domains where even…