ISSN :2582-9793

Enhancing Embedding Performance through Large Language Model-based Text Enrichment and Rewriting

Original Research (Published On: 29-Jun-2024 )
Enhancing Embedding Performance through Large Language Model-based Text Enrichment and Rewriting
DOI : https://dx.doi.org/10.54364/AAIML.2024.42136

Syed Muhammad Yousaf Hashmy and Nicholas Harris

Adv. Artif. Intell. Mach. Learn., 4 (2):2358-2368

Syed Muhammad Yousaf Hashmy : Arizona State University

Nicholas Harris : Arizona State University

Download PDF Here

DOI: https://dx.doi.org/10.54364/AAIML.2024.42136

Article History: Received on: 16-Apr-24, Accepted on: 22-Jun-24, Published on: 29-Jun-24

Corresponding Author: Syed Muhammad Yousaf Hashmy

Email: shashmy@asu.edu

Citation: Nicholas Harris, Anand Butani, Syed Muhammad Yousaf Hashmy (2024). Enhancing Embedding Performance through Large Language Model-based Text Enrichment and Rewriting. Adv. Artif. Intell. Mach. Learn., 4 (2 ):2358-2368

          

Abstract

    

Embedding models are crucial for various natural language processing tasks but can be limited by factors such as limited vocabulary, lack of context, and grammatical errors. This paper proposes a novel approach to improve embedding performance by leveraging large language models (LLMs) to enrich and rewrite input text before the embedding process. By utilizing ChatGPT 3.5 to provide additional context, correct inaccuracies, and incorporate metadata, the proposed method aims to enhance the utility and accuracy of embedding models. The effectiveness of this approach is evaluated on three datasets: Banking77Classification, TwitterSemEval 2015, and Amazon Counter-factual Classification. The results demonstrate significant improvements over the baseline model on the TwitterSemEval 2015 dataset, with the best-performing prompt achieving an average precision based on cosine similarity score of 85.34 compared to the previous best of 81.52 on the Massive Text Embedding Benchmark (MTEB) Leaderboard.} However, performance on the other two datasets i.e.  Banking77Classification and Amazon Counter Factual was less impressive. The findings suggest that LLM-based text enrichment has shown promising results to improve embedding performance, particularly in certain domains. Hence, numerous limitations in the process of embedding can be avoided.

Statistics

   Article View: 85
   PDF Downloaded: 0