arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.09760cs.CL
收藏

ConFit v3:通过基于LLM的重排序提升简历-岗位匹配

ConFit v3: Improving Resume-Job Matching with LLM-based Re-Ranking

Columbia University(哥伦比亚大学);John Hopkins University(约翰霍普金斯大学);Intellipro Group Inc.(Intellipro集团)

Xiao Yu, Ruize Xu, Chengyuan Xue, Junyu Chen, Matthew So, Shijun Ma, Bo Liu, Xiangye Liang, Zhou Yu

AI总结:

本文提出ConFit v3,通过改进重排序算法和数据处理方法,提升简历与岗位匹配的准确性,优于现有最佳系统和大型语言模型。

摘要:

一个可靠的简历-岗位匹配系统能帮助公司从简历池中找到合适候选人,也能帮助求职者从岗位列表中找到相关职位。尽管基于嵌入的方法如ConFit和ConFit v2能高效地大规模检索候选人,但缺乏可控性和可解释性限制了其在现实中的应用。基于LLM的重排序器可通过推理解决这些限制,但现有训练方法是在短文档基准上开发的,未考虑现实招聘数据中的噪声。本文首先对LLM重排序器的训练管道进行了系统分析,涵盖推理算法设计、RL算法选择、数据处理和SFT蒸馏。我们发现使用多轮重排序、使用列表式RL目标进行训练、去除噪声样本以及在RL前从更强的LLM蒸馏显著提升了重排序性能。我们随后将这些发现汇总,使用Qwen3-8B和Qwen3-32B在现实的简历-岗位匹配数据集上训练ConFit v3,并发现其在现有最佳简历-岗位匹配系统以及大型语言模型如GPT-5和Claude Opus-4.5上均有显著提升。我们希望我们的发现能为未来研究LLM重排序器适应简历-岗位匹配系统提供有用见解。

英文摘要:

A reliable resume-job matching system helps a company find suitable candidates from a pool of resumes and helps a job seeker find relevant jobs from a list of job posts. While recent advances in embedding-based methods such as ConFit and ConFit v2 can efficiently retrieve candidates at scale, the lack of controllability and explainability limits their real-world adaptations. LLM-based re-rankers can address these limitations through reasoning, but existing training recipes are developed on short-document benchmarks and do not account for noise in real-world recruiting data. In this work, we first conduct a systematic analysis over the LLM re-ranker training pipeline for person-job fit, covering inference algorithm design, RL algorithm selection, data processing, and SFT distillation. We find that using multi-pass re-ranking, training with listwise RL objectives, removing noisy samples, and distilling from a stronger LLM before RL significantly improves re-ranking performance. We then aggregate these findings to train ConFit v3 with Qwen3-8B and Qwen3-32B on real-world person-job fit datasets, and find significant improvements over existing best person-job fit systems as well as strong LLMs such as GPT-5 and Claude Opus-4.5. We hope our findings provide useful insights for future research on adapting LLM-based re-rankers to person-job fit systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑