Automated Code Generation for Tabular Question Answering in Zero-Shot Settings

• Roi Santos-Ríos ^[1] ; Adrián Gude ^[1] ; Francisco Prado-Valiño ^[1] ; Ana Ezquerro ^[1] ; Jesús Vilares ^[1]
  1. [1] Universidade da Coruña

     Universidade da Coruña

     A Coruña, España

     
• Localización: Proceedings XoveTIC 2025: Impulsando el talento científico / coord. por Manuel Lagos Rodríguez, Hilda Romero-Velo, Álvaro Leitao , Javier Pereira-Loureiro , Manuel Penedo , 2026, ISBN 978-84-9749-925-5, págs. 391-398
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • Our work presents an effective and robust approach to Tabular Question Answering based on a zero-shot pipeline that uses a Large Language Model to generate executable code for extracting information from tables. Our system includes a modular architecture: a code generation module supported by column selection and type inference components to guide accurate code synthesis, together with an iterative repair mechanism for runtime errors into revised prompts. Our approach is successfully tested both in English and Spanish.