aiqbench analysis
This study demonstrates a practical application of Large Language Models for text-to-SQL tasks within the astronomical domain, specifically enabling natural language querying of complex databases like ALeRCE. By implementing a four-module framework with self-correction capabilities, researchers achieved high accuracy on simple queries while identifying specific performance drops as query complexity increases across thirteen evaluated models. The work highlights current limitations in handling hard logical constraints but validates LLMs as viable tools for accelerating data analysis in scientific research communities.
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 database. ALeRCE is a community broker for the Zwicky Transient Facility and the Vera C. Rubin Observatory. The system enables users to query the database in natural language (NL) and generates executable SQL queries. To develop and evaluate the system, we constructed a dataset of 110 NL/SQL pairs. We propose a step-by-step generation framework comprising four modules: schema linking, query classification, prompt decomposition, and self-correction. The performance of thirteen LLMs is evaluated using in-context learning and prompt engineering techniques. Text-to-SQL performance is assessed using the perfect-match (PM) rate for row identifiers (e.g., object identifiers) and column identifiers (i.e., column names). The proposed step-by-step framework consistently outperforms a direct-inference baseline, while the self-correction module consistently reduces execution errors. For Claude Opus 4.6, PM performance on row (column) identifiers is high for simple queries, reaching 0.97 (0.94), and decreases with query complexity to 0.44 (0.72) for medium queries and 0.59 (0.49) for hard queries. Among the thirteen evaluated models, the best-performing LLMs for the text-to-SQL task are Claude Opus 4.6, Gemini 2.5 Pro, Gemini 3 Flash, and GPT-5.2-Codex.
Authors: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
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 database. ALeRCE is a community broker for the Zwicky Transient Facility and the Vera C. Rubin Observatory. The system enables users to query the database in natural language (NL) and generates executable SQL queries. To develop and evaluate the system, we constructed a dataset of 110 NL/SQL pairs. We propose a step-by-step generation framework comprising four modules: schema linking, query classification, prompt decomposition, and self-correction. The performance of thirteen LLMs is evaluated using in-context learning and prompt engineering techniques. Text-to-SQL performance is assessed using the perfect-match (PM) rate for row identifiers (e.g., object identifiers) and column identifiers (i.e., column names). The proposed step-by-step framework consistently outperforms a direct-inference baseline, while the self-correction module consistently reduces execution errors. For Claude Opus 4.6, PM performance on row (column) identifiers is high for simple queries, reaching 0.97 (0.94), and decreases with query complexity to 0.44 (0.72) for medium queries and 0.59 (0.49) for hard queries. Among the thirteen evaluated models, the best-performing LLMs for the text-to-SQL task are Claude Opus 4.6, Gemini 2.5 Pro, Gemini 3 Flash, and GPT-5.2-Codex.
Instrumentation and Methods for Astrophysics (astro-ph.IM); Artificial Intelligence (cs.AI)
arXiv:2606.18108 [astro-ph.IM]
(or arXiv:2606.18108v1 [astro-ph.IM] for this version)
https://doi.org/10.48550/arXiv.2606.18108 arXiv-issued DOI via DataCite (pending registration)
From: Pablo Estevez Prof. [view email] [v1] Tue, 16 Jun 2026 16:12:16 UTC (1,276 KB)
Full text under the publisher's open licence · 275 words