Text Summarization Using LLM

Utsha Sarker (), Lalit Vaishnav (), Archy Biswas (), Ashish Raj; Saurabh () and Saurabh ()

International Journal of Innovative Science and Research Technology (IJISRT), 2025, vol. 10, issue 11, 1193-1198

Abstract: The main reason for the high effectiveness of text summarization is due to the success of LLMs for this task and across different domains. This work aims at understanding how LLMs are used to summarize domains and make it more accurate and efficient. We discuss how current models perform with regard to specialized information, with focus on the financial and medical domains. The work suggests that an approach using Vertex AI, a generative machine learning platform in the cloud, can be used to assess pre-trained summarization models for different tasks. Most of the research presented in the paper also reveals the efficacy of Vertex AI for text summarization with high accuracy and efficiency. We demonstrate the applicability of the platform for summarizing transcripts and dialogues, generating bullet points, titles and to- do lists. Also, the research show that Vertex AI is reliable in terms of cost since it can be used by businesses and individual researchers.

Keywords: LLM; Summarization; Domain-Specific; Vertex AI; Generative Models; ML; NLP; Finance; Healthcare; Evaluation; ROUGE; Cloud-Based; AI; Data Science; Text Mining. (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.ijisrt.com/text-summarization-using-llm (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:cvr:ijisrt:2025:11:ijisrt25nov797

DOI: 10.38124/ijisrt/25nov797

Access Statistics for this article

More articles in International Journal of Innovative Science and Research Technology (IJISRT) from IJISRT Publication
Bibliographic data for series maintained by Rahul Goyel ().