2025 08 21

Five papers accepted by EMNLP 2025 (4x Main & 1x Findings): (1) LMR-BENCH: Evaluating LLM Agent’s Ability on Reproducing Language Modeling Research; (2) MedFact: A Large-scale Chinese Dataset for Evidence-based Medical Fact-checking of LLM Responses; (3) Can GRPO Boost Complex Multimodal Table Understanding?; (4) WISE: Weak-Supervision-Guided Step-by-Step Explanations for Multimodal LLMs in Image Classification; (5) NUMINA: A Natural Understanding Benchmark for Multi-dimensional Intelligence and Numerical Reasoning Abilities.