用新架构和大模型蒸馏，实现长简历实时精准匹配岗位。
An Efficient Long-Context Ranking Architecture With Calibrated LLM Distillation: Application to Person-Job Fit
- 采用晚期交叉注意力分解长文本，计算开销小
- 大模型生成细粒度监督信号，提升匹配准确性
- 适合需要实时、可解释人岗匹配的招聘场景
在实时匹配求职者与岗位时，面对长篇、结构化且多语言的简历，挑战巨大。本文提出一种基于新一代晚期交叉注意力架构的重排序模型，通过分解简历与项目简介，高效处理长上下文输入，计算开销极低。为缓解历史数据偏差，采用生成式大语言模型（LLM）作为教师，生成细粒度、语义连贯的监督信号，并通过增强型蒸馏损失函数注入学生模型。最终模型输出技能契合度评分，实现一致且可解释的人岗匹配。在相关性、排序与校准指标上的实验表明，本方法优于现有最优基线。
原文摘要 · Abstract (English)
Finding the most relevant person for a job proposal in real time is challenging, especially when resumes are long, structured, and multilingual. In this paper, we propose a re-ranking model based on a new generation of late cross-attention architecture, that decomposes both resumes and project briefs to efficiently handle long-context inputs with minimal computational overhead. To mitigate historical data biases, we use a generative large language model (LLM) as a teacher, generating fine-grained, semantically grounded supervision. This signal is distilled into our student model via an enriched distillation loss function. The resulting model produces skill-fit scores that enable consistent and interpretable person-job matching. Experiments on relevance, ranking, and calibration metrics demonstrate that our approach outperforms state-of-the-art baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。