MORE-R1: Guiding LVLM for Multimodal Object-Entity Relation Extraction via Stepwise Reasoning with Reinforcement Learning

TL;DR

This paper introduces MORE-R1, a novel LVLM model that employs explicit stepwise reasoning with reinforcement learning to improve multimodal object-entity relation extraction, achieving state-of-the-art results.

Contribution

The paper proposes a new model with a two-stage training process incorporating reinforcement learning and stepwise reasoning for better multimodal relation extraction.

Findings

Achieves state-of-the-art performance on the MORE benchmark.

Demonstrates significant improvement over existing methods.

Effectively models complex reasoning in multimodal scenarios.

Abstract

Multimodal Object-Entity Relation Extraction (MORE) is a challenging task in information extraction research. It aims to identify relations between visual objects and textual entities, requiring complex multimodal understanding and cross-modal reasoning abilities. Existing methods, mainly classification-based or generation-based without reasoning, struggle to handle complex extraction scenarios in the MORE task and suffer from limited scalability and intermediate reasoning transparency. To address these challenges, we propose MORE-R1, a novel model that introduces explicit stepwise reasoning with Reinforcement Learning (RL) to enable Large Vision-Language Model (LVLM) to address the MORE task effectively. MORE-R1 integrates a two-stage training process, including an initial cold-start training stage with Supervised Fine-Tuning (SFT) and a subsequent RL stage for reasoning ability optimization. In the initial stage, we design an efficient way to automatically construct a high-quality SFT dataset containing fine-grained stepwise reasoning tailored to the MORE task, enabling the model to learn an effective reasoning paradigm. In the subsequent stage, we employ the Group Relative Policy Optimization (GRPO) RL algorithm with a Progressive Sample-Mixing Strategy to stabilize training and further enhance model's reasoning ability on hard samples. Comprehensive experiments on the MORE benchmark demonstrate that MORE-R1 achieves state-of-the-art performance with significant improvement over baselines.