PulseAugur
EN
LIVE 07:27:55

LLMs power new text-to-SQL system for astronomical databases

By PulseAugur Editorial · [1 sources] ·

Researchers have developed a text-to-SQL system leveraging large language models for querying astronomical databases, specifically the ALeRCE system for the Zwicky Transient Facility and Vera C. Rubin Observatory. The system, which uses in-context learning, allows users to input natural language queries to generate executable SQL. A dataset of 110 NL/SQL pairs was created to evaluate the framework, which includes modules for schema linking, query classification, prompt decomposition, and self-correction. Performance tests on thirteen LLMs showed that Claude Opus 4.6, Gemini 2.5 Pro, Gemini 3 Flash, and GPT-5.2-Codex were the top performers, with Claude Opus 4.6 achieving high accuracy on simpler queries but decreasing with complexity. AI

IMPACT Enables natural language querying of complex scientific databases, potentially accelerating research in fields like astronomy.

RANK_REASON The cluster describes a research paper detailing a new system and evaluation of LLMs for a specific scientific application. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

COVERAGE [1]

  1. 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