RankPO: Preference Optimization for Job-Talent Matching

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Yafei, Wang, Murray, Wang, Yu, Wang, Xiaohui
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917956712136704
author Zhang, Yafei
Wang, Murray
Wang, Yu
Wang, Xiaohui
author_facet Zhang, Yafei
Wang, Murray
Wang, Yu
Wang, Xiaohui
contents Matching job descriptions (JDs) with suitable talent requires models capable of understanding not only textual similarities between JDs and candidate resumes but also contextual factors such as geographical location and academic seniority. To address this challenge, we propose a two-stage training framework for large language models (LLMs). In the first stage, a contrastive learning approach is used to train the model on a dataset constructed from real-world matching rules, such as geographical alignment and research area overlap. While effective, this model primarily learns patterns that defined by the matching rules. In the second stage, we introduce a novel preference-based fine-tuning method inspired by Direct Preference Optimization (DPO), termed Rank Preference Optimization (RankPO), to align the model with AI-curated pairwise preferences emphasizing textual understanding. Our experiments show that while the first-stage model achieves strong performance on rule-based data (nDCG@20 = 0.706), it lacks robust textual understanding (alignment with AI annotations = 0.46). By fine-tuning with RankPO, we achieve a balanced model that retains relatively good performance in the original tasks while significantly improving the alignment with AI preferences. The code and data are available at https://github.com/yflyzhang/RankPO.
format Preprint
id arxiv_https___arxiv_org_abs_2503_10723
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RankPO: Preference Optimization for Job-Talent Matching
Zhang, Yafei
Wang, Murray
Wang, Yu
Wang, Xiaohui
Computation and Language
Artificial Intelligence
Information Retrieval
Machine Learning
Matching job descriptions (JDs) with suitable talent requires models capable of understanding not only textual similarities between JDs and candidate resumes but also contextual factors such as geographical location and academic seniority. To address this challenge, we propose a two-stage training framework for large language models (LLMs). In the first stage, a contrastive learning approach is used to train the model on a dataset constructed from real-world matching rules, such as geographical alignment and research area overlap. While effective, this model primarily learns patterns that defined by the matching rules. In the second stage, we introduce a novel preference-based fine-tuning method inspired by Direct Preference Optimization (DPO), termed Rank Preference Optimization (RankPO), to align the model with AI-curated pairwise preferences emphasizing textual understanding. Our experiments show that while the first-stage model achieves strong performance on rule-based data (nDCG@20 = 0.706), it lacks robust textual understanding (alignment with AI annotations = 0.46). By fine-tuning with RankPO, we achieve a balanced model that retains relatively good performance in the original tasks while significantly improving the alignment with AI preferences. The code and data are available at https://github.com/yflyzhang/RankPO.
title RankPO: Preference Optimization for Job-Talent Matching
topic Computation and Language
Artificial Intelligence
Information Retrieval
Machine Learning
url https://arxiv.org/abs/2503.10723