Exploring Large Language Models for Product Attribute Value Identification

TL;DR

This paper investigates the use of large language models like LLaMA and Mistral for product attribute value identification, proposing prompt strategies and fine-tuning methods that improve zero-shot and supervised performance.

Contribution

It introduces a two-step prompt approach and instruction fine-tuning for LLMs, enhancing their effectiveness and data efficiency in product attribute value identification tasks.

Findings

Two-step prompt approach improves zero-shot accuracy

Instruction fine-tuning boosts performance with training data

LLM-based methods outperform traditional fine-tuning approaches

Abstract

Product attribute value identification (PAVI) involves automatically identifying attributes and their values from product information, enabling features like product search, recommendation, and comparison. Existing methods primarily rely on fine-tuning pre-trained language models, such as BART and T5, which require extensive task-specific training data and struggle to generalize to new attributes. This paper explores large language models (LLMs), such as LLaMA and Mistral, as data-efficient and robust alternatives for PAVI. We propose various strategies: comparing one-step and two-step prompt-based approaches in zero-shot settings and utilizing parametric and non-parametric knowledge through in-context learning examples. We also introduce a dense demonstration retriever based on a pre-trained T5 model and perform instruction fine-tuning to explicitly train LLMs on task-specific instructions. Extensive experiments on two product benchmarks show that our two-step approach significantly improves performance in zero-shot settings, and instruction fine-tuning further boosts performance when using training data, demonstrating the practical benefits of using LLMs for PAVI.