Metraipolis › archive › dc_48a7fc01db7b

Q&A on Any Spreadsheet Requires Interpreting Its Grid Structure — arXiv:2609.20732

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.20732
License (as archived)
CC0-1.0
Archived
2026-10-10T03:22:20.671Z
SHA-256 of the archived text
afbf18e5dcb40a5f2cddd93431614e99a85bae9793a816a922c540f47adc8146
Stable URL of this page
https://metraipolis.com/documento/dc_48a7fc01db7b

How to cite

Q&A on Any Spreadsheet Requires Interpreting Its Grid Structure — arXiv:2609.20732 — arXiv (en), https://arxiv.org/abs/2609.20732 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_48a7fc01db7b (Metraipolis archive dc_48a7fc01db7b, sha256 afbf18e5dcb40a5f2cddd93431614e99a85bae9793a816a922c540f47adc8146)
BibTeX
@misc{dc48a7fc01db7b,
  title = {Q&A on Any Spreadsheet Requires Interpreting Its Grid Structure — arXiv:2609.20732},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.20732},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_48a7fc01db7b; sha256 afbf18e5dcb40a5f2cddd93431614e99a85bae9793a816a922c540f47adc8146},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20732. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Semantic cell annotation improves chunking interpretability for spreadsheets in LLM-driven RAG systems, aiding answer generation through enriched context rather than improved retrieval accuracy. We propose a novel framework of splitting any spreadsheet into interpretable chunks using cell role annotation. Our framework beats the state of the art, yet it faces a hard ceiling. Spreadsheets are fundamentally two-dimensional unstructured data with continuous relationships and infinite potential cell roles. Because classification models are restricted to finite, pre-defined classes, they cannot perfectly capture this structural nuance, even with human-level annotation. We show that addressing the spreadsheet-to-LLM bottleneck requires moving beyond discrete cell classification. Instead, the field must develop dimensionality-reduction techniques to directly flatten 2D unstructured spreadsheets into 1D unstructured text. Text chunks would be easier for downstream RAG to interpret and generate from.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2609.20732 — 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 2026-10-10T03:04:13.759Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).