Metraipolis › archive › dc_99db608e6d05

Self-Refining Prompt Induction for Streaming Text-to-SQL — arXiv:2611.00960

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00960
License (as archived)
CC0-1.0
Archived
2026-11-03T10:35:34.373Z
SHA-256 of the archived text
65a740880479b99e51029d49fa00286e32aa523697c88e7d8b4f2faa19c49f8e
Stable URL of this page
https://metraipolis.com/documento/dc_99db608e6d05

How to cite

Self-Refining Prompt Induction for Streaming Text-to-SQL — arXiv:2611.00960 — arXiv (en), https://arxiv.org/abs/2611.00960 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_99db608e6d05 (Metraipolis archive dc_99db608e6d05, sha256 65a740880479b99e51029d49fa00286e32aa523697c88e7d8b4f2faa19c49f8e)
BibTeX
@misc{dc99db608e6d05,
  title = {Self-Refining Prompt Induction for Streaming Text-to-SQL — arXiv:2611.00960},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00960},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_99db608e6d05; sha256 65a740880479b99e51029d49fa00286e32aa523697c88e7d8b4f2faa19c49f8e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00960. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Text-to-SQL assistants for streaming engines must handle dialect-specific types, windowing rules, and temporal semantics, including constructs poorly handled by generic prompts. We present Self-Refining Prompt Induction (SRPI), an offline method that converts generation failures into reusable dialect instructions while keeping model weights fixed. A Refiner revises the Generator's prompt using reference-conditioned feedback from three LLM judges; a sampled regression guard checks earlier successes, and a separate Compressor reduces prompt length. Inference uses the frozen prompt without retrieval or query repair. We evaluate cross-domain and cross-model transfer on Confluent Cloud Flink SQL using a controlled synthetic workload seeded by 30 expert-written examples, with 335 induction examples and 257 questions from held-out domains. The same induced prompt improves mean judge scores across seven Generators by 7.1-19.2 percentage points, including an increase from 85.3% to 97.5% for the induction model. A separate compression study reduces prompt length by 52.7% with a 0.19-percentage-point score decrease. An assistant using the induced prompt is in early access, with initial user feedback to inform subsequent refinement.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Databases (cs.DB).
Pagina del lavoro: https://arxiv.org/abs/2611.00960 — 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 2026-11-03T10:29:48.737Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).