Home / Current Issue / Paper 1709005
Enhancing Recruitment Drive Query Summarization: Benchmarking Models
Subject area: Science,Engineering and Technology · Area of research: Machine Learning
Abstract
Campus recruitment is an important life phase from a student perspective. Not only students, but the institute conducting the process also aspires to be the top institute providing recruitment to various talented minds across the globe. Training and placement cell from various institutes manages this process with the help of various authoritative persons. For every organization recruiting through campus placement drive, the process starts with registration and ends with the successful hiring of the candidates. During this process, students face various difficulties and complications at every stage of recruitment drive. Every authoritative person receives multiple queries to address the difficulties faced by the students. Leveraging text summarization to summarize the queries and resolve the difficulties in a short span of time proves to be useful for both the parties. This paper encompasses the use of various Large Language Models for summarizing the queries and benchmarking them against the standard metrics.
Keywords
Text Summarization, Large Language Models, Queries, BERT.
How to cite this paper
@article{1709005,
author = {Atharva Sadanand Litake, Apurva Ajit Kulkarni, Kishanlal Chhelaram Choudhary, Aditya Ashru Darade, Dr. Geetanjali Kale; Prof. Pranali Rajendra Navghare},
title = {Enhancing Recruitment Drive Query Summarization: Benchmarking Models},
journal = {Iconic Research And Engineering Journals},
year = {2025},
volume = {8},
number = {12},
pages = {131-137},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1709005.pdf},
abstract = {Campus recruitment is an important life phase from a student perspective. Not only students, but the institute conducting the process also aspires to be the top institute providing recruitment to various talented minds across the globe. Training and placement cell from various institutes manages this process with the help of various authoritative persons. For every organization recruiting through campus placement drive, the process starts with registration and ends with the successful hiring of the candidates. During this process, students face various difficulties and complications at every stage of recruitment drive. Every authoritative person receives multiple queries to address the difficulties faced by the students. Leveraging text summarization to summarize the queries and resolve the difficulties in a short span of time proves to be useful for both the parties. This paper encompasses the use of various Large Language Models for summarizing the queries and benchmarking them against the standard metrics.},
keywords = {Text Summarization, Large Language Models, Queries, BERT.},
month = {June},
}