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

TL;DR

This paper enhances resume-job matching by systematically optimizing LLM-based re-ranking techniques, leading to significant performance improvements over existing systems and large language models.

Contribution

It provides a comprehensive analysis of training strategies for LLM re-rankers and introduces ConFit v3 with improved methods for real-world person-job fit applications.

Findings

Multi-pass re-ranking improves accuracy.

Listwise RL objectives outperform other training methods.

Training with stronger LLMs and data cleaning enhances performance.

Abstract

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.