用多模块框架提升招聘广告中的技能词抽取准确率
Job Skill Extraction via LLM-Centric Multi-Module Framework
- 融合语义检索、上下文学习与微调，生成规范输出
- 在6个数据集上严格准确率显著优于GPT-3.5基线
- 适合低资源、跨领域场景的可靠技能抽取应用
从职位广告中进行细粒度技能抽取是实现求职者与岗位匹配及劳动力市场分析的关键，但生成式大模型常出现跨度错误、边界偏移和幻觉问题，尤其在长尾术语和跨领域场景下表现不佳。我们提出SRICL框架，结合语义检索（SR）、上下文学习（ICL）和监督微调（SFT），并引入确定性验证器。SR从ESCO中获取本域标注句与定义，构建格式约束提示，稳定边界并处理共现关系；SFT对齐输出行为，验证器通过最小重试次数强制保证配对、无重叠和BIO格式合法性。在涵盖多个行业和语言的六个公开职位句子数据集上，SRICL相比GPT-3.5提示基线取得显著的STRICT-F1提升，大幅减少无效标签与幻觉跨度，支持在低资源、多领域环境下可靠部署。
原文摘要 · Abstract (English)
Span-level skill extraction from job advertisements underpins candidate-job matching and labor-market analytics, yet generative large language models (LLMs) often yield malformed spans, boundary drift, and hallucinations, especially with long-tail terms and cross-domain shift. We present SRICL, an LLM-centric framework that combines semantic retrieval (SR), in-context learning (ICL), and supervised fine-tuning (SFT) with a deterministic verifier. SR pulls in-domain annotated sentences and definitions from ESCO to form format-constrained prompts that stabilize boundaries and handle coordination. SFT aligns output behavior, while the verifier enforces pairing, non-overlap, and BIO legality with minimal retries. On six public span-labeled corpora of job-ad sentences across sectors and languages, SRICL achieves substantial STRICT-F1 improvements over GPT-3.5 prompting baselines and sharply reduces invalid tags and hallucinated spans, enabling dependable sentence-level deployment in low-resource, multi-domain settings.
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。