Information Retrieval Performance in Text Generation using Knowledge from Generative Pre-trained Transformer (GPT-3)

Abstract

The rise of advanced language models like GPT-3 and text generation has witnessed remarkable progress. However, leveraging the vast amount of knowledge within these models to enhance information retrieval performance remains an area that needs to be explored. This research used Artificial Intelligence, specifically the OpenAI GPT-3 language model, to create an application to help make written content. This research investigates the impact of incorporating GPT-3's knowledge into text generation processes and evaluates its influence on information retrieval tasks. Several features in text generation generate text that requires exact information, such as specifications for a product and accurate descriptions of a job or product, which are included in the concept of information retrieval in text creation by language models. The research used the few-shot learning method in the GPT-3 language model. The generated responses are then evaluated using established information retrieval metrics such as precision, recall, and F1-score. The findings of this research reveal the effectiveness of utilizing GPT-3's knowledge in enhancing information retrieval performance. The generated responses demonstrate improved relevance to user queries, resulting in the same performance precision and recall scores compared to other paid text generator websites. Application results are testing in capabilities of retrieving some information. Application capabilities tested on other commercial text generator engines. The test results obtained BERTscore 86\% (precision), 88\% (recall), and 87\% (F1-Score).