Enhancing Online Recruitment with Category-Aware MoE and LLM-based Data Augmentation

2026-04-23

AI Summary

This study addresses the significant limitations in job-candidate matching performance caused by low-quality job descriptions and highly similar candidate-job pairs in online recruitment. To tackle this issue, the authors propose a large language model (LLM)-based data augmentation approach leveraging chain-of-thought prompting to rewrite poor-quality job postings. Additionally, they introduce a Category-Aware Mixture-of-Experts (MoE) architecture that dynamically adjusts expert weights by integrating category embeddings, thereby enhancing matching discriminability. Experimental results demonstrate that the proposed method improves offline evaluation metrics by 2.40% in AUC and 7.46% in GAUC, while achieving a 19.4% increase in online click-through conversion rate. The approach has also led to substantial cost savings—amounting to millions of RMB—for recruiters, confirming its effectiveness and practical value.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Search and Optimization: Learning to Search
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Person-Job Fit (PJF) is a critical component for online recruitment. Existing approaches face several challenges, particularly in handling low-quality job descriptions and similar candidate-job pairs, which impair model performance. To address these challenges, this paper proposes a large language model (LLM) based method with two novel techniques: (1) LLM-based data augmentation, which polishes and rewrites low-quality job descriptions by leveraging chain-of-thought (COT) prompts, and (2) category-aware Mixture of Experts (MoE) that assists in identifying similar candidate-job pairs. This MoE module incorporates category embeddings to dynamically assign weights to the experts and learns more distinguishable patterns for similar candidate-job pairs. We perform offline evaluations and online A/B tests on our recruitment platform. Our method relatively surpasses existing methods by 2.40% in AUC and 7.46% in GAUC, and boosts click-through conversion rate (CTCVR) by 19.4% in online tests, saving millions of CNY in external headhunting expenses.

Problem

• Person-Job Fit
• low-quality job descriptions
• similar candidate-job pairs
• online recruitment

Innovation

• LLM-based data augmentation
• Category-Aware MoE
• Chain-of-Thought prompting
• Person-Job Fit
• Online recruitment