Metraipolis › archive › dc_e0ef86cd64cd

EAR: Entity-Aware Partitioning Approach for Retrieval-Augmented Generation Development — arXiv:2609.12268

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.12268
License (as archived): CC0-1.0
Archived: 2026-10-16T03:08:19.375Z
SHA-256 of the archived text: 0c1fa57b69dc7a5391f895c868b65df19c0bfe4ee52007fcbca100d249ec0016
Stable URL of this page: https://metraipolis.com/documento/dc_e0ef86cd64cd

How to cite

EAR: Entity-Aware Partitioning Approach for Retrieval-Augmented Generation Development — arXiv:2609.12268 — arXiv (en), https://arxiv.org/abs/2609.12268 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e0ef86cd64cd (Metraipolis archive dc_e0ef86cd64cd, sha256 0c1fa57b69dc7a5391f895c868b65df19c0bfe4ee52007fcbca100d249ec0016)

BibTeX

@misc{dce0ef86cd64cd,
  title = {EAR: Entity-Aware Partitioning Approach for Retrieval-Augmented Generation Development — arXiv:2609.12268},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12268},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e0ef86cd64cd; sha256 0c1fa57b69dc7a5391f895c868b65df19c0bfe4ee52007fcbca100d249ec0016},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12268. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Retrieval-augmented generation (RAG) can improve knowledge-intensive question answering, but the first design choice is easy to overlook: how should the source corpus be partitioned into retrievable units? Fixed-size chunks often return long passages whose relation to the question is only implicit. We introduce EAR, an Entity-Aware Partitioning approach for multiple-choice question answering (MCQA). EAR extracts normalized surface anchors from the question, answer options, and corpus; retrieves local windows around matching corpus anchors; and can attach a larger parent passage through an extractive summary. We evaluate EAR on a cleaned Massive Multitask Language Understanding (MMLU)-style subset of 153 questions selected by an automatic corpus-support heuristic and using decontaminated public textbook text. Across same-protocol top-k = 3 and top-k = 8 sweeps with Mistral, Gemma, and DeepSeek, EAR entity-window reduces retrieved words by 37.5-40.2% relative to chunks. Observed accuracy changes are +5.2, +1.3, and -3.9 points at top-k = 3, and +5.9, -3.3, and -4.6 points at top-k = 8; none of the entity-window differences is statistically significant. The scoped contribution is methodological: EAR provides a compact and inspectable retrieval unit, while its rule-based anchor extractor remains domain-specific and requires separate validation before transfer.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.12268 — 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 2026-10-16T03:02:47.533Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).