Exploring Large Language Models for Product Attribute Value Identification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910612408238080 |
|---|---|
| author | Sabeh, Kassem Kacimi, Mouna Gamper, Johann Litschko, Robert Plank, Barbara |
| author_facet | Sabeh, Kassem Kacimi, Mouna Gamper, Johann Litschko, Robert Plank, Barbara |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_12695 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Exploring Large Language Models for Product Attribute Value Identification Sabeh, Kassem Kacimi, Mouna Gamper, Johann Litschko, Robert Plank, Barbara Computation and Language Information Retrieval 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. |
| title | Exploring Large Language Models for Product Attribute Value Identification |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2409.12695 |