activity
20242026
most citedWhich Changes Matter? Towards Trustworthy Legal AI via Relevance-Sensitive Evaluation and Solver-Grounded Reasoning

1 citations · 1 across the 4 of their papers we have counts for

collaborators

7 papers

cs.AI2026

X-RAY: Mapping LLM Reasoning Capability via Formalized and Calibrated Probes

Tianxi Gao, Yufan Cai, Yusi Yuan +1

Large language models (LLMs) achieve promising performance, yet their ability to reason remains poorly understood. Existing evaluations largely emphasize task-level accuracy, often…

cs.AI20261 cited

Which Changes Matter? Towards Trustworthy Legal AI via Relevance-Sensitive Evaluation and Solver-Grounded Reasoning

Chen Linze, Cai Yufan, Hou Zhe +1

Legal reasoning requires distinguishing changes that matter from those that do not. Legal AI should remain stable under legally irrelevant perturbations, but should change when per…

eess.IV2026

A Clinically Validated Foundation Model for Comprehensive Lung Pathology Interpretation

Zhengrui Guo, Zhengyu Zhang, Jiabo Ma +23

Pathological assessment guides lung cancer diagnosis, treatment selection, and prognostic evaluation, yet current CPath approaches rely on task-specific models for isolated objecti…

cs.AI2026

Uncertainty Reasoning with Large Language Models for Explainable Disease Diagnosis

Xiaoyang Fan, Yufan Cai, Zhe Hou +1

Clinical decision-making requires reasoning over incomplete, imprecise, and linguistically expressed patient narratives. While large language models (LLMs) excel at extracting late…

cs.AI2026

Towards Trustworthy Legal AI through LLM Agents and Formal Reasoning

Linze Chen, Yufan Cai, Zhe Hou +1

Legal decisions should be logical and based on statutory laws. While large language models(LLMs) are good at understanding legal text, they cannot provide verifiable justifications…

cs.SE2025

PAT-Agent: Autoformalization for Model Checking

Xinyue Zuo, Yifan Zhang, Hongshu Wang +4

Recent advances in large language models (LLMs) offer promising potential for automating formal methods. However, applying them to formal verification remains challenging due to th…