EIVEN: Efficient Implicit Attribute Value Extraction using Multimodal LLM

TL;DR

EIVEN is a novel multimodal LLM framework that efficiently extracts implicit product attribute values from images and text, reducing data needs and improving accuracy in e-commerce applications.

Contribution

The paper introduces EIVEN, a parameter-efficient multimodal LLM framework with a Learning-by-Comparison technique for implicit attribute extraction, and provides open-source datasets for this task.

Findings

EIVEN outperforms existing methods in accuracy.

Requires less labeled data for training.

Effective in extracting implicit attribute values.

Abstract

In e-commerce, accurately extracting product attribute values from multimodal data is crucial for improving user experience and operational efficiency of retailers. However, previous approaches to multimodal attribute value extraction often struggle with implicit attribute values embedded in images or text, rely heavily on extensive labeled data, and can easily confuse similar attribute values. To address these issues, we introduce EIVEN, a data- and parameter-efficient generative framework that pioneers the use of multimodal LLM for implicit attribute value extraction. EIVEN leverages the rich inherent knowledge of a pre-trained LLM and vision encoder to reduce reliance on labeled data. We also introduce a novel Learning-by-Comparison technique to reduce model confusion by enforcing attribute value comparison and difference identification. Additionally, we construct initial open-source datasets for multimodal implicit attribute value extraction. Our extensive experiments reveal that EIVEN significantly outperforms existing methods in extracting implicit attribute values while requiring less labeled data.