Saved in:
Bibliographic Details
Main Authors: Yu, Xiao, Xu, Ruize, Xue, Chengyuan, Zhang, Jinzhong, Ma, Xu, Yu, Zhou
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.12361
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917942253322240
author Yu, Xiao
Xu, Ruize
Xue, Chengyuan
Zhang, Jinzhong
Ma, Xu
Yu, Zhou
author_facet Yu, Xiao
Xu, Ruize
Xue, Chengyuan
Zhang, Jinzhong
Ma, Xu
Yu, Zhou
contents A reliable resume-job matching system helps a company recommend suitable candidates from a pool of resumes and helps a job seeker find relevant jobs from a list of job posts. However, since job seekers apply only to a few jobs, interaction labels in resume-job datasets are sparse. We introduce ConFit v2, an improvement over ConFit to tackle this sparsity problem. We propose two techniques to enhance the encoder's contrastive training process: augmenting job data with hypothetical reference resume generated by a large language model; and creating high-quality hard negatives from unlabeled resume/job pairs using a novel hard-negative mining strategy. We evaluate ConFit v2 on two real-world datasets and demonstrate that it outperforms ConFit and prior methods (including BM25 and OpenAI text-embedding-003), achieving an average absolute improvement of 13.8% in recall and 17.5% in nDCG across job-ranking and resume-ranking tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2502_12361
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ConFit v2: Improving Resume-Job Matching using Hypothetical Resume Embedding and Runner-Up Hard-Negative Mining
Yu, Xiao
Xu, Ruize
Xue, Chengyuan
Zhang, Jinzhong
Ma, Xu
Yu, Zhou
Computation and Language
A reliable resume-job matching system helps a company recommend suitable candidates from a pool of resumes and helps a job seeker find relevant jobs from a list of job posts. However, since job seekers apply only to a few jobs, interaction labels in resume-job datasets are sparse. We introduce ConFit v2, an improvement over ConFit to tackle this sparsity problem. We propose two techniques to enhance the encoder's contrastive training process: augmenting job data with hypothetical reference resume generated by a large language model; and creating high-quality hard negatives from unlabeled resume/job pairs using a novel hard-negative mining strategy. We evaluate ConFit v2 on two real-world datasets and demonstrate that it outperforms ConFit and prior methods (including BM25 and OpenAI text-embedding-003), achieving an average absolute improvement of 13.8% in recall and 17.5% in nDCG across job-ranking and resume-ranking tasks.
title ConFit v2: Improving Resume-Job Matching using Hypothetical Resume Embedding and Runner-Up Hard-Negative Mining
topic Computation and Language
url https://arxiv.org/abs/2502.12361