Metraipolis › archive › dc_394defd6680d

From Data Querying to Data Investigations: Rethinking Natural Language Interfaces for Databases — arXiv:2609.03898

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03898
License (as archived)
CC0-1.0
Archived
2026-10-17T03:00:45.086Z
SHA-256 of the archived text
20f6dbc5561ad07e05face32643249cf297f7be02e5d2248490c2c4b192ff625
Stable URL of this page
https://metraipolis.com/documento/dc_394defd6680d

How to cite

From Data Querying to Data Investigations: Rethinking Natural Language Interfaces for Databases — arXiv:2609.03898 — arXiv (en), https://arxiv.org/abs/2609.03898 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_394defd6680d (Metraipolis archive dc_394defd6680d, sha256 20f6dbc5561ad07e05face32643249cf297f7be02e5d2248490c2c4b192ff625)
BibTeX
@misc{dc394defd6680d,
  title = {From Data Querying to Data Investigations: Rethinking Natural Language Interfaces for Databases — arXiv:2609.03898},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03898},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_394defd6680d; sha256 20f6dbc5561ad07e05face32643249cf297f7be02e5d2248490c2c4b192ff625},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03898. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Natural language (NL) interfaces to databases have been optimized for the wrong problem. The dominant Text-to-SQL paradigm assumes that users ask questions that can be answered by single SQL queries. In practice, however, users seek assistance with solving data problems. This requires searching a database by sequences of SQL queries while reasoning over intermediate results instead of just running one SQL query. This paper therefore introduces a new paradigm for NL interfaces to data, which we call data investigations. We present D^2, a first prototype of a data investigation system that embodies this vision by autonomously searching, reasoning over, and collecting data to solve data problems. Using a newly constructed benchmark based on the Murder Mystery dataset, we demonstrate the potential of D^2 for tasks that require data investigations with evidence-backed decisions, extending beyond the capabilities of traditional single-query question answering.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-04 in cs.DB).
Categorie arXiv: Databases (cs.DB).
Pagina del lavoro: https://arxiv.org/abs/2609.03898 — 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 2026-10-17T02:33:39.146Z dalla pagina https://arxiv.org/catchup/cs.DB/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).