Search papers, labs, and topics across Lattice.
This paper introduces a novel approach to Person-Job Fit (PJF) in online recruitment by using LLMs for data augmentation of low-quality job descriptions via chain-of-thought prompting and a category-aware Mixture of Experts (MoE) to better identify similar candidate-job pairs. The category-aware MoE uses category embeddings to dynamically weight experts, improving the model's ability to distinguish similar pairs. Experiments on a real-world recruitment platform demonstrate a 2.40% AUC and 7.46% GAUC improvement, along with a 19.4% boost in click-through conversion rate.
LLMs can rewrite bad job descriptions and category-aware MoEs can better match candidates, leading to a 19.4% boost in recruitment click-through rates and millions saved.
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.