Metraipolis › archive › dc_140eef664ebc
RDL-Bench: A Benchmark for Task-Aware Question Answering over Relational Databases — arXiv:2610.21382
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.21382
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T10:22:29.406Z
- SHA-256 of the archived text
8f8c12b7e419d114f1b86e656de9448e85f1d44fc3825faa2ab58aaa35dcf253- Stable URL of this page
https://metraipolis.com/documento/dc_140eef664ebc
How to cite
RDL-Bench: A Benchmark for Task-Aware Question Answering over Relational Databases — arXiv:2610.21382 — arXiv (en), https://arxiv.org/abs/2610.21382 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_140eef664ebc (Metraipolis archive dc_140eef664ebc, sha256 8f8c12b7e419d114f1b86e656de9448e85f1d44fc3825faa2ab58aaa35dcf253)
BibTeX
@misc{dc140eef664ebc,
title = {RDL-Bench: A Benchmark for Task-Aware Question Answering over Relational Databases — arXiv:2610.21382},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.21382},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_140eef664ebc; sha256 8f8c12b7e419d114f1b86e656de9448e85f1d44fc3825faa2ab58aaa35dcf253},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21382. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Relational databases (RDBs) remain the primary infrastructure for storing and managing structured data across enterprise and scientific domains. Natural-language (NL) interfaces to RDBs aim to let users ask questions without writing SQL, but real user needs go beyond SQL-style lookup: some questions require reasoning over the observable database state, while others require predictive inference from historical relational records under temporal constraints. Existing benchmarks address these goals in isolation. To address this gap, we introduce RDL-Bench, a benchmark for task-aware question answering (QA) over real RDBs. RDL-Bench organizes diverse user questions into reasoning-oriented questions, whose answers are determined by the current database state, and prediction-oriented questions, whose answers depend on future outcomes under temporal constraints. Each instance contains an NL question, task metadata, schema information, temporal context, either executable evidence or target-construction logic, and denotation-level ground truth. RDL-Bench supports two evaluation settings: native solvers under their intended capabilities, and task-aware modular systems where a router dispatches each question to an appropriate execution module. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.21382 — 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 2026-10-16T08:48:02.711Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).