Tzu-Yen Ma

THEMIS: Towards Holistic Evaluation of MLLMs for Scientific Paper Fraud Forensics

We present **THEMIS**, a novel multi-task benchmark designed to comprehensively evaluate Multimodal Large Language Models (MLLMs) on visual fraud reasoning within real-world academic scenarios. Compared to existing benchmarks, THEMIS introduces three major advancements. (1) **Real-world Scenarios &…