Job Skill Extraction via LLM-Centric Multi-Module Framework
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913057778696192 |
|---|---|
| author | Li, Guojing Fu, Zichuan Li, Junyi Liu, Faxue Zhou, Wenxia Wang, Yejing Gao, Jingtong Wang, Maolin Liu, Rungen Zhang, Wenlin Zhao, Xiangyu |
| author_facet | Li, Guojing Fu, Zichuan Li, Junyi Liu, Faxue Zhou, Wenxia Wang, Yejing Gao, Jingtong Wang, Maolin Liu, Rungen Zhang, Wenlin Zhao, Xiangyu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_21525 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Job Skill Extraction via LLM-Centric Multi-Module Framework Li, Guojing Fu, Zichuan Li, Junyi Liu, Faxue Zhou, Wenxia Wang, Yejing Gao, Jingtong Wang, Maolin Liu, Rungen Zhang, Wenlin Zhao, Xiangyu Computation and Language 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. |
| title | Job Skill Extraction via LLM-Centric Multi-Module Framework |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.21525 |