AI RESEARCH
Can GRPO Boost Complex Multimodal Table Understanding?
arXiv CS.CL
•
ArXi:2509.16889v3 Announce Type: replace Existing table understanding methods face challenges due to complex table structures and intricate logical reasoning. While supervised finetuning (SFT) dominates existing research, reinforcement learning (RL), such as Group Relative Policy Optimization (GRPO), has shown promise but struggled with low initial policy accuracy and coarse rewards in tabular contexts. In this paper, we