Automated Code Generation for Tabular Question Answering in Zero-Shot Settings
| UDC.coleccion | Publicacións UDC | |
| UDC.conferenceTitle | XoveTIC: impulsando el talento científico (8º. 2025. A Coruña) | |
| UDC.departamento | Ciencias da Computación e Tecnoloxías da Información | |
| UDC.endPage | 397 | |
| UDC.grupoInv | Lingua e Sociedade da Información (LYS) | |
| UDC.institutoCentro | CITIC - Centro de Investigación de Tecnoloxías da Información e da Comunicación | |
| UDC.startPage | 391 | |
| dc.contributor.author | Santos-Ríos, Roi | |
| dc.contributor.author | López Gude, Adrián | |
| dc.contributor.author | Prado-Valiño, Francisco | |
| dc.contributor.author | Ezquerro, Ana | |
| dc.contributor.author | Vilares, Jesús | |
| dc.date.accessioned | 2026-09-04T15:57:16Z | |
| dc.date.available | 2026-09-04T15:57:16Z | |
| dc.date.issued | 2025 | |
| dc.description | Presentado en: VIII Congreso Xove TIC: impulsando el talento científico. Octubre, 2025, A Coruña. | |
| dc.description.abstract | [Abstract]: 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. | |
| dc.description.sponsorship | We acknowledge grants SCANNER-UDC (PID2020-113230RB-C21) funded by MICIU/AEI/10.13039/501100011033; GAP (PID2022-139308OA-I00) funded by MICIU/AEI/10.13039/501100011033/ and ERDF, EU; LATCHING (PID2023-147129OB-C21) funded by MICIU/AEI/10.13039/501100011033 and ERDF, EU; CIDMEFEO funded by the Spanish National Statistics Institute (INE); as well as funding by Xunta de Galicia (ED431C 2024/02). CITIC, as a center accredited for excellence within the Galician University System and a member of the CIGUS Network, receives subsidies from the Department of Education, Science, Universities, and Vocational Training of the Xunta de Galicia. Additionally, it is co-financed by the EU through the FEDER Galicia 2021-27 operational program (ED431G 2023/01). | |
| dc.description.sponsorship | Xunta de Galicia; ED431G 2023/01 | |
| dc.description.sponsorship | Xunta de Galicia; ED431C 2024/02 | |
| dc.identifier.citation | Ríos, R. S., Gude, A., Valiño, F. P., Ezquerro, A. X. N. P., & Vilares, J. (2026). Automated Code Generation for Tabular Question Answering in Zero-Shot Settings. In Proceedings XoveTIC 2025: Impulsando el talento científico (pp. 391-398). Servizo de Publicacións UDC. https://doi.org/10.17979/spu.23.c60. | |
| dc.identifier.doi | 10.17979/spu.23.c60 | |
| dc.identifier.isbn | 978-84-9749-925-5 | |
| dc.identifier.uri | https://hdl.handle.net/2183/49166 | |
| dc.language.iso | eng | |
| dc.publisher | Universidade da Coruña, Servizo de Publicacións | |
| dc.relation.projectID | info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2020-113230RB-C21/ES/MODELOS MULTITAREA DE ETIQUETADO SECUENCIAL PARA EL RECONOCIMIENTO DE ENTIDADES ENRIQUECIDO CON INFORMACION LINGUISTICA: SINTAXIS E INTEGRACION MULTITAREA (SCANNER-UDC) | |
| dc.relation.projectID | info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023/PID2023-147129OB-C21/ES/TECNOLOGÍAS DEL LENGUAJE DESDE UNA PERSPECTIVA VERDE (LATCHING): DOMINIOS CON ESCASOS RECURSOS | |
| dc.relation.projectID | info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023/PID2022-139308OA-100/ES/REPRESENTACIONES ESTRUCTURADAS VERDES Y ENCHUFABLES | |
| dc.relation.uri | https://doi.org/10.17979/spu.23.c60 | |
| dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 International | en |
| dc.rights.accessRights | open access | |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | |
| dc.subject | Tabular question answering | |
| dc.subject | Large Language Models (LLMs) | |
| dc.subject | Automated code generation | |
| dc.subject | Zero-shot learning | |
| dc.subject | Executable code synthesis | |
| dc.title | Automated Code Generation for Tabular Question Answering in Zero-Shot Settings | |
| dc.type | conference output | |
| dspace.entity.type | Publication | |
| relation.isAuthorOfPublication | 2f08b56a-af5a-4627-b111-5ccccc33d17d | |
| relation.isAuthorOfPublication | 3313b723-2288-4d9d-b0e7-32732c9c78d5 | |
| relation.isAuthorOfPublication.latestForDiscovery | 2f08b56a-af5a-4627-b111-5ccccc33d17d |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- XoveTIC_2025_proceedings_c60.pdf
- Size:
- 1.85 MB
- Format:
- Adobe Portable Document Format

