LyS at SemEval 2025 Task 8: Zero-Shot Code Generation for Tabular QA
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911102944673792 |
|---|---|
| author | Gude, Adrián Santos-Ríos, Roi Prado-Valiño, Francisco Ezquerro, Ana Vilares, Jesús |
| author_facet | Gude, Adrián Santos-Ríos, Roi Prado-Valiño, Francisco Ezquerro, Ana Vilares, Jesús |
| contents | This paper describes our participation in SemEval 2025 Task 8, focused on Tabular Question Answering. We developed a zero-shot pipeline that leverages an Large Language Model to generate functional code capable of extracting the relevant information from tabular data based on an input question. Our approach consists of a modular pipeline where the main code generator module is supported by additional components that identify the most relevant columns and analyze their data types to improve extraction accuracy. In the event that the generated code fails, an iterative refinement process is triggered, incorporating the error feedback into a new generation prompt to enhance robustness. Our results show that zero-shot code generation is a valid approach for Tabular QA, achieving rank 33 of 53 in the test phase despite the lack of task-specific fine-tuning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_09012 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LyS at SemEval 2025 Task 8: Zero-Shot Code Generation for Tabular QA Gude, Adrián Santos-Ríos, Roi Prado-Valiño, Francisco Ezquerro, Ana Vilares, Jesús Computation and Language Artificial Intelligence Machine Learning This paper describes our participation in SemEval 2025 Task 8, focused on Tabular Question Answering. We developed a zero-shot pipeline that leverages an Large Language Model to generate functional code capable of extracting the relevant information from tabular data based on an input question. Our approach consists of a modular pipeline where the main code generator module is supported by additional components that identify the most relevant columns and analyze their data types to improve extraction accuracy. In the event that the generated code fails, an iterative refinement process is triggered, incorporating the error feedback into a new generation prompt to enhance robustness. Our results show that zero-shot code generation is a valid approach for Tabular QA, achieving rank 33 of 53 in the test phase despite the lack of task-specific fine-tuning. |
| title | LyS at SemEval 2025 Task 8: Zero-Shot Code Generation for Tabular QA |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2508.09012 |