Metraipolis › archive › dc_ff8bb073dbdd

REAP: Relation-Aware Elicitation and Parsing for Closed-Book Knowledge Base Construction from LLMs — arXiv:2608.10963

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.10963
License (as archived): CC0-1.0
Archived: 2026-10-19T06:14:24.647Z
SHA-256 of the archived text: 473fafc0b4d815f98212a3d2cf6b48acac0d9356ea5d57db9be1ce975aad9d23
Stable URL of this page: https://metraipolis.com/documento/dc_ff8bb073dbdd

How to cite

REAP: Relation-Aware Elicitation and Parsing for Closed-Book Knowledge Base Construction from LLMs — arXiv:2608.10963 — arXiv (en), https://arxiv.org/abs/2608.10963 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff8bb073dbdd (Metraipolis archive dc_ff8bb073dbdd, sha256 473fafc0b4d815f98212a3d2cf6b48acac0d9356ea5d57db9be1ce975aad9d23)

BibTeX

@misc{dcff8bb073dbdd,
  title = {REAP: Relation-Aware Elicitation and Parsing for Closed-Book Knowledge Base Construction from LLMs — arXiv:2608.10963},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10963},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff8bb073dbdd; sha256 473fafc0b4d815f98212a3d2cf6b48acac0d9356ea5d57db9be1ce975aad9d23},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10963. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present the REAP system for the AKBC Shared Task 2026 on constructing knowledge bases from language models in a closed-book setting, subject to a budget of at most 32B parameters and no model fine-tuning. Our system combines structured chain-of-thought reasoning, relation-specific query strategies, and a reasoning-based empty-set gate to elicit parametric knowledge, followed by direct extraction into valid JSON arrays. On the test set, the system, built on the Mistral-Small-24B-Instruct-2501 model, achieves a macro-F1 score of 0.62, with particularly strong results on countryLandBordersCountry (F1 = 0.95), companyTradesAtStockExchange (F1 = 0.73), and hasArea (F1 = 0.77). Our code is publicly available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.10963 — 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 2026-10-19T06:08:50.334Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).