Enhancing Talent Search Ranking with Role-Aware Expert Mixtures and LLM-based Fine-Grained Job Descriptions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Jihang, Xu, Bing, Chen, Zulong, Xu, Chuanfei, Chen, Minping, Liu, Suyu, Zhou, Ying, Wen, Zeyi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917113334071296
author Li, Jihang
Xu, Bing
Chen, Zulong
Xu, Chuanfei
Chen, Minping
Liu, Suyu
Zhou, Ying
Wen, Zeyi
author_facet Li, Jihang
Xu, Bing
Chen, Zulong
Xu, Chuanfei
Chen, Minping
Liu, Suyu
Zhou, Ying
Wen, Zeyi
contents Talent search is a cornerstone of modern recruitment systems, yet existing approaches often struggle to capture nuanced job-specific preferences, model recruiter behavior at a fine-grained level, and mitigate noise from subjective human judgments. We present a novel framework that enhances talent search effectiveness and delivers substantial business value through two key innovations: (i) leveraging LLMs to extract fine-grained recruitment signals from job descriptions and historical hiring data, and (ii) employing a role-aware multi-gate MoE network to capture behavioral differences across recruiter roles. To further reduce noise, we introduce a multi-task learning module that jointly optimizes click-through rate (CTR), conversion rate (CVR), and resume matching relevance. Experiments on real-world recruitment data and online A/B testing show relative AUC gains of 1.70% (CTR) and 5.97% (CVR), and a 17.29% lift in click-through conversion rate. These improvements reduce dependence on external sourcing channels, enabling an estimated annual cost saving of millions of CNY.
format Preprint
id arxiv_https___arxiv_org_abs_2512_00004
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Talent Search Ranking with Role-Aware Expert Mixtures and LLM-based Fine-Grained Job Descriptions
Li, Jihang
Xu, Bing
Chen, Zulong
Xu, Chuanfei
Chen, Minping
Liu, Suyu
Zhou, Ying
Wen, Zeyi
Information Retrieval
Artificial Intelligence
Machine Learning
Talent search is a cornerstone of modern recruitment systems, yet existing approaches often struggle to capture nuanced job-specific preferences, model recruiter behavior at a fine-grained level, and mitigate noise from subjective human judgments. We present a novel framework that enhances talent search effectiveness and delivers substantial business value through two key innovations: (i) leveraging LLMs to extract fine-grained recruitment signals from job descriptions and historical hiring data, and (ii) employing a role-aware multi-gate MoE network to capture behavioral differences across recruiter roles. To further reduce noise, we introduce a multi-task learning module that jointly optimizes click-through rate (CTR), conversion rate (CVR), and resume matching relevance. Experiments on real-world recruitment data and online A/B testing show relative AUC gains of 1.70% (CTR) and 5.97% (CVR), and a 17.29% lift in click-through conversion rate. These improvements reduce dependence on external sourcing channels, enabling an estimated annual cost saving of millions of CNY.
title Enhancing Talent Search Ranking with Role-Aware Expert Mixtures and LLM-based Fine-Grained Job Descriptions
topic Information Retrieval
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2512.00004