用多智能体辩论提升电商隐式属性提取准确率
MADIAVE: Multi-Agent Debate for Implicit Attribute Value Extraction
- 多个大模型智能体通过辩论迭代优化属性推断
- 少量辩论轮次显著提升低性能属性准确率
- 适合需要高精度多模态属性提取的电商场景
隐式属性值抽取（Implicit AVE）对精准表示电商商品至关重要，需从多模态数据中推断潜在属性。尽管多模态大模型（MLLM）取得进展，但因数据维度复杂且视觉-文本理解存在鸿沟，隐式 AVE 仍具挑战。本文提出 MADIAVE，一种多智能体辩论框架，利用多个 MLLM 智能体通过多轮辩论迭代修正推理结果。实验在 ImplicitAVE 数据集上显示，仅数轮辩论即显著提升准确率，尤其改善初始表现较差的属性。系统评估了不同配置（相同或异构 MLLM、辩论轮数），分析其收敛动态。结果表明，多智能体辩论可有效克服单智能体局限，为多模态电商中的隐式 AVE 提供可扩展解决方案。
原文摘要 · Abstract (English)
Implicit Attribute Value Extraction (AVE) is essential for accurately representing products in e-commerce, as it infers latent attributes from multimodal data. Despite advances in multimodal large language models (MLLMs), implicit AVE remains challenging due to the complexity of multidimensional data and gaps in vision-text understanding. In this work, we introduce MADIAVE, a multi-agent debate framework that employs multiple MLLM agents to iteratively refine inferences. Through a series of debate rounds, agents verify and update each other's responses, thereby improving inference performance and robustness. Experiments on the ImplicitAVE dataset demonstrate that even a few rounds of debate significantly boost accuracy, especially for attributes with initially low performance. We systematically evaluate various debate configurations, including identical or different MLLM agents, and analyze how debate rounds affect convergence dynamics. Our findings highlight the potential of multi-agent debate strategies to address the limitations of single-agent approaches and offer a scalable solution for implicit AVE in multimodal e-commerce.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。