Metraipolis › archive › dc_f0141ae691e7

Page-Aware Retrieval-Augmented Generation for EvalLLM 2026: A Five-Variant Study on French PDFs — arXiv:2609.34776

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34776
License (as archived)
CC0-1.0
Archived
2026-10-07T20:58:09.647Z
SHA-256 of the archived text
c9a00170c4a5bc85333ac060bcfabb222959fd9ec77d9241fd6241cb659cb258
Stable URL of this page
https://metraipolis.com/documento/dc_f0141ae691e7

How to cite

Page-Aware Retrieval-Augmented Generation for EvalLLM 2026: A Five-Variant Study on French PDFs — arXiv:2609.34776 — arXiv (en), https://arxiv.org/abs/2609.34776 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f0141ae691e7 (Metraipolis archive dc_f0141ae691e7, sha256 c9a00170c4a5bc85333ac060bcfabb222959fd9ec77d9241fd6241cb659cb258)
BibTeX
@misc{dcf0141ae691e7,
  title = {Page-Aware Retrieval-Augmented Generation for EvalLLM 2026: A Five-Variant Study on French PDFs — arXiv:2609.34776},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34776},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f0141ae691e7; sha256 c9a00170c4a5bc85333ac060bcfabb222959fd9ec77d9241fd6241cb659cb258},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34776. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study retrieval-augmented generation (RAG) for questions about French PDF documents when both the answer and its supporting document pages are evaluated. Five system variants add dense retrieval, rank fusion, reranking, and query decomposition to a BM25 baseline. On 595 challenge questions, the complete system scores 0.4450 MRR@10 and 0.4013 Recall@10, compared with 0.3430 and 0.2994 for BM25. Dense retrieval alone and a simple lexical--dense fusion both underperform BM25. Reranking improves the hybrid system, whereas adding query decomposition produces the largest further gain, with higher latency and more detected output artifacts. The complete system slightly exceeds the reported anonymous overall mean on two answer metrics but falls below it on most page-retrieval metrics. These results identify accurate page selection, rather than semantic retrieval in isolation, as the main opportunity for improvement in this setting.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.34776 — 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 2026-10-07T20:29:01.660Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).