计算机应用研究2026，Vol.43Issue(6)：1601-1608,8.DOI:10.19734/j.issn.1001-3695.2025.10.0436
Impli-R1:结合多模态推理的隐性属性值抽取方法
Impli-R1:multi-modal reasoning-driven method for implicit attribute value extraction
摘要
Abstract
Multimodal attribute value extraction plays a crucial role in applications such as e-commerce,search engines,and automated product categorization,aiming to identify attribute-value pairs from product descriptions.Traditional approaches mainly focus on explicit attributes whose values are directly presented in text or images,however,with the growing diversity of data,extracting implicit attributes has become an increasingly important research direction.Unlike explicit attributes,implicit attributes are not directly observable and require multimodal reasoning and semantic associations for identification,while exis ting methods still struggle with complex cross-modal reasoning and information fusion.To address these challenges,this paper proposed Impli-R1,which introduced a systematic multimodal reasoning mechanism into implicit attribute value extraction by leveraging high-quality long chain-of-thought reasoning samples and adopting a hybrid training strategy that combined super-vised fine-tuning and reinforcement learning,further enhanced by a group-based reward strategy to improve the granularity and robustness of reasoning.Experimental results show that Impli-R1 significantly outperforms existing methods in terms of Micro-F1 on both the ChiImpAVE and ImplicitAVE benchmark datasets,demonstrating its effectiveness and generalization ability in multimodal implicit attribute value extraction.关键词
多模态属性值抽取/多模态推理/监督微调/强化学习Key words
multimodal attribute value extraction/multimodal reasoning/supervised fine-tuning/reinforcement learning分类
信息技术与安全科学引用本文复制引用
陈奇,于碧辉,魏靖烜,王海广,史慧洋,伍高巍,孙林壮..Impli-R1:结合多模态推理的隐性属性值抽取方法[J].计算机应用研究,2026,43(6):1601-1608,8.基金项目
沈阳市科学技术计划-社会治理科技专项(23-407-3-29) （23-407-3-29）
