eC-Tab2Text: Aspect-Based Text Generation from e-Commerce Product Tables

TL;DR

This paper introduces eC-Tab2Text, a new dataset for e-commerce text generation from product tables, demonstrating how fine-tuned LLMs can produce accurate, attribute-specific product reviews, thus advancing e-commerce automation.

Contribution

The paper presents eC-Tab2Text, a domain-specific dataset for e-commerce, and shows how fine-tuning LLMs on this dataset improves product review generation from structured data.

Findings

Significant improvement in review accuracy and faithfulness.

Enhanced fluency and contextual relevance of generated reviews.

Demonstrated effectiveness of domain-specific datasets for LLM fine-tuning.

Abstract

Large Language Models (LLMs) have demonstrated exceptional versatility across diverse domains, yet their application in e-commerce remains underexplored due to a lack of domain-specific datasets. To address this gap, we introduce eC-Tab2Text, a novel dataset designed to capture the intricacies of e-commerce, including detailed product attributes and user-specific queries. Leveraging eC-Tab2Text, we focus on text generation from product tables, enabling LLMs to produce high-quality, attribute-specific product reviews from structured tabular data. Fine-tuned models were rigorously evaluated using standard Table2Text metrics, alongside correctness, faithfulness, and fluency assessments. Our results demonstrate substantial improvements in generating contextually accurate reviews, highlighting the transformative potential of tailored datasets and fine-tuning methodologies in optimizing e-commerce workflows. This work highlights the potential of LLMs in e-commerce workflows and the essential role of domain-specific datasets in tailoring them to industry-specific challenges.