用多模型分段精调提升简历解析准确率
MSLEF: Multi-Segment LLM Ensemble Finetuning in Recruitment
- 分段精调多个大模型，按简历不同部分分配专用模型
- 在招聘相似度上比单模型最高提升7%，多指标全面领先
- 适合需要高精度简历自动解析的招聘系统开发者
本文提出MSLEF，一种用于招聘自动化中简历解析的多段集成微调框架。该框架通过加权投票整合多个微调的大语言模型（LLMs），每个模型专注于简历的特定段落以提升准确性。基于MLAR，MSLEF引入段落感知架构，针对不同简历部分采用领域特异性加权，有效克服单一模型在多样格式下的局限性。框架采用Gemini-2.5-Flash作为高层聚合器处理复杂段落，结合Gemma 9B、LLaMA 3.1 8B和Phi-4 14B模型。在精确匹配（EM）、F1分数、BLEU、ROUGE及招聘相似度（RS）等指标上均显著提升，其中在RS上优于最优单模型高达+7%。其段落感知设计增强了对多样化简历布局的泛化能力，适用于真实招聘场景，确保候选人信息的精准可靠表达。
原文摘要 · Abstract (English)
This paper presents MSLEF, a multi-segment ensemble framework that employs LLM fine-tuning to enhance resume parsing in recruitment automation. It integrates fine-tuned Large Language Models (LLMs) using weighted voting, with each model specializing in a specific resume segment to boost accuracy. Building on MLAR , MSLEF introduces a segment-aware architecture that leverages field-specific weighting tailored to each resume part, effectively overcoming the limitations of single-model systems by adapting to diverse formats and structures. The framework incorporates Gemini-2.5-Flash LLM as a high-level aggregator for complex sections and utilizes Gemma 9B, LLaMA 3.1 8B, and Phi-4 14B. MSLEF achieves significant improvements in Exact Match (EM), F1 score, BLEU, ROUGE, and Recruitment Similarity (RS) metrics, outperforming the best single model by up to +7% in RS. Its segment-aware design enhances generalization across varied resume layouts, making it highly adaptable to real-world hiring scenarios while ensuring precise and reliable candidate representation.
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。