Metraipolis › archive › dc_d71faf297447

Structure then Query: Enabling Precise Analytical Queries over Unstructured Documents — arXiv:2608.13384

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13384
License (as archived)
CC0-1.0
Archived
2026-10-19T04:55:14.960Z
SHA-256 of the archived text
3dadfc74d5846ea2f02b996628e5db96f963c0f30a355a8e78576faf7e358b95
Stable URL of this page
https://metraipolis.com/documento/dc_d71faf297447

How to cite

Structure then Query: Enabling Precise Analytical Queries over Unstructured Documents — arXiv:2608.13384 — arXiv (en), https://arxiv.org/abs/2608.13384 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d71faf297447 (Metraipolis archive dc_d71faf297447, sha256 3dadfc74d5846ea2f02b996628e5db96f963c0f30a355a8e78576faf7e358b95)
BibTeX
@misc{dcd71faf297447,
  title = {Structure then Query: Enabling Precise Analytical Queries over Unstructured Documents — arXiv:2608.13384},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13384},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d71faf297447; sha256 3dadfc74d5846ea2f02b996628e5db96f963c0f30a355a8e78576faf7e358b95},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13384. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Unstructured documents constitute the majority of enterprise and web data. With the rapid development of large language models(LLMs), researchers have started to build data systems that analyze unstructured textual documents like operating on databases. However, because mainstream retrieval methods still relies on fuzzy matching based on vector similarity, accurately obtaining information and performing structured analysis and reasoning remains a major challenge. To address these limitations, AnnoIndex introduces two core fundamental components. The first is Annotation Index. The system uses a module called SchemaLoop to automatically create hierarchical annotation schemas from the raw corpus, and then uses lightweight language model to extract specific values. It turns scattered unstructured text into a materialized, structured index that enables low-cost filtering and querying. The annotation index avoids the black-box matching of vector similarity and amortizes attribute extraction costs from online queries to a one-time build. The second innovation is a Structured Query Engine. It compiles user questions into execution plans based on SQL extension. It first uses the Annotation Index for precise documents filtering, then gradually applies extraction operations in ascending order of cost, resorting to LLMs only for the remaining minimal fraction of the corpus that require deep semantic understanding. The extracted attributions are merged into the annotation index, reducing the cost of future queries. Experiments on three real-world datasets demonstrate that AnnoIndex consistently outperforms state-of-the-art baselines, achieving the highest average F1 score (0.87) while maintaining robust performance on complex multi-hop join and progressive reasoning queries.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-14 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR) ; Databases (cs.DB).
Pagina del lavoro: https://arxiv.org/abs/2608.13384 — 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 2026-10-19T04:46:09.757Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).