Comparative Study of Domain Driven Terms Extraction Using Large Language Models

TL;DR

This study compares the effectiveness of three large language models in extracting domain-specific keywords from datasets, highlighting the importance of prompt engineering and addressing challenges like hallucination and resource demands.

Contribution

It provides a comparative analysis of Llama2-7B, GPT-3.5, and Falcon-7B for keyword extraction using LLMs, with performance evaluation on Inspec and PubMed datasets.

Findings

GPT-3.5 achieved the highest Jaccard scores on both datasets.

Prompt engineering significantly influences keyword extraction quality.

Challenges include model complexity, resource use, and hallucination effects.

Abstract

Keywords play a crucial role in bridging the gap between human understanding and machine processing of textual data. They are essential to data enrichment because they form the basis for detailed annotations that provide a more insightful and in-depth view of the underlying data. Keyword/domain driven term extraction is a pivotal task in natural language processing, facilitating information retrieval, document summarization, and content categorization. This review focuses on keyword extraction methods, emphasizing the use of three major Large Language Models(LLMs): Llama2-7B, GPT-3.5, and Falcon-7B. We employed a custom Python package to interface with these LLMs, simplifying keyword extraction. Our study, utilizing the Inspec and PubMed datasets, evaluates the performance of these models. The Jaccard similarity index was used for assessment, yielding scores of 0.64 (Inspec) and 0.21 (PubMed) for GPT-3.5, 0.40 and 0.17 for Llama2-7B, and 0.23 and 0.12 for Falcon-7B. This paper underlines the role of prompt engineering in LLMs for better keyword extraction and discusses the impact of hallucination in LLMs on result evaluation. It also sheds light on the challenges in using LLMs for keyword extraction, including model complexity, resource demands, and optimization techniques.