PulseAugur
EN
LIVE 09:46:35

LLMs power text-to-SQL for astronomical database queries

By PulseAugur Editorial · [2 sources] ·

Researchers have developed a text-to-SQL system leveraging large language models to query astronomical databases, specifically the ALeRCE system for the Zwicky Transient Facility and Vera C. Rubin Observatory. The system translates natural language questions into executable SQL queries, employing a novel step-by-step generation framework that includes schema linking, query classification, prompt decomposition, and self-correction. Evaluations showed that this framework outperforms direct inference, with Claude Opus 4.6, Gemini 2.5 Pro, Gemini 3 Flash, and GPT-5.2 Codex being the top-performing models for this task. AI

IMPACT This research demonstrates LLMs' capability in specialized data querying, potentially streamlining scientific research workflows.

RANK_REASON The cluster reports on a research paper detailing a new system and its evaluation.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

LLMs power text-to-SQL for astronomical database queries

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · P. A. Estevez, J. Espejo-Moreira, S. Sanfeliu-Alvarez, F. Forster, A. M. Munoz Arancibia, G. Cabrera-Vives, F. E. Bauer, A. Bayo, M. Catelan, R. Dastidar, L. Hernandez-Garcia, J. A. Intriago, G. Pignata ·

    Querying an astronomical database using large language models: the ALeRCE text-to-SQL system

    arXiv:2606.18108v1 Announce Type: cross Abstract: We develop a text-to-SQL (structured query language) system based on large language models (LLMs) using in-context learning and apply it to the Automatic Learning for the Rapid Classification of Events (ALeRCE) astronomical databa…

  2. arXiv cs.AI TIER_1 English(EN) · G. Pignata ·

    Querying an astronomical database using large language models: the ALeRCE text-to-SQL system

    We develop a text-to-SQL (structured query language) system based on large language models (LLMs) using in-context learning and apply it to the Automatic Learning for the Rapid Classification of Events (ALeRCE) astronomical database. ALeRCE is a community broker for the Zwicky Tr…

RELATED ENTITIES

RELATED TOPICS