Metraipolis › archive › dc_6a3189eef780
From Lexical Baselines to Agentic Retrieval-Augmented Generation: Structured Skill and Responsibility-Level Extraction with the SFIA Framework — arXiv:2609.35806
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.35806
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T16:24:39.779Z
- SHA-256 of the archived text
c3abcb92ea28ccc9329c2716f1c7b7c5a0927a929c8725e964cda74c030d5049- Stable URL of this page
https://metraipolis.com/documento/dc_6a3189eef780
How to cite
From Lexical Baselines to Agentic Retrieval-Augmented Generation: Structured Skill and Responsibility-Level Extraction with the SFIA Framework — arXiv:2609.35806 — arXiv (en), https://arxiv.org/abs/2609.35806 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6a3189eef780 (Metraipolis archive dc_6a3189eef780, sha256 c3abcb92ea28ccc9329c2716f1c7b7c5a0927a929c8725e964cda74c030d5049)
BibTeX
@misc{dc6a3189eef780,
title = {From Lexical Baselines to Agentic Retrieval-Augmented Generation: Structured Skill and Responsibility-Level Extraction with the SFIA Framework — arXiv:2609.35806},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.35806},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6a3189eef780; sha256 c3abcb92ea28ccc9329c2716f1c7b7c5a0927a929c8725e964cda74c030d5049},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35806. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Automated skill extraction underpins workforce planning, yet most systems represent skills as flat labels with no notion of the responsibility level at which a skill is practiced. The Skills Framework for the Information Age (SFIA) captures exactly this dimension, defining 147 professional skills across seven responsibility levels, but no automated LLM-based extraction targeting SFIA has been reported. We formalize the task as structured prediction of (skill, level) pairs from free text and ask three questions: how accurately can text be mapped onto SFIA's closed vocabulary, which strategies reliably predict the level alongside the skill, and do agentic designs improve on simpler retrieval and prompting? We evaluate five strategies (a lexical baseline, dense retrieval with LLM reranking, a zero-shot schema-constrained LLM, single-agent agentic RAG, and a three-agent retriever--matcher--verifier crew) against expert-mapped European ICT role profiles, all drawing on an SFIA~9 corpus built by a fully automated agentic pipeline that we release. Retrieval-based matching identifies the most skills while generative strategies are markedly more precise; only strategies assigning the level as an explicit decision predict it reliably, with similarity-based selection more than twice as inaccurate; and the crew doubles latency without improving accuracy, so added agent roles do not automatically benefit closed-taxonomy matching. These results provide the first reproducible baseline for structured, level-aware skill extraction against SFIA. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.35806 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T15:54:53.706Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).