AILS-NTUA at SemEval-2025 Task 8: Language-to-Code prompting and Error Fixing for Tabular Question Answering
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916874328997888 |
|---|---|
| author | Evangelatos, Andreas Filandrianos, Giorgos Lymperaiou, Maria Voulodimos, Athanasios Stamou, Giorgos |
| author_facet | Evangelatos, Andreas Filandrianos, Giorgos Lymperaiou, Maria Voulodimos, Athanasios Stamou, Giorgos |
| contents | In this paper, we present our submission to SemEval-2025 Task 8: Question Answering over Tabular Data. This task, evaluated on the DataBench dataset, assesses Large Language Models' (LLMs) ability to answer natural language questions over structured data while addressing topic diversity and table size limitations in previous benchmarks. We propose a system that employs effective LLM prompting to translate natural language queries into executable code, enabling accurate responses, error correction, and interpretability. Our approach ranks first in both subtasks of the competition in the proprietary model category, significantly outperforming the organizer's baseline. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_00435 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AILS-NTUA at SemEval-2025 Task 8: Language-to-Code prompting and Error Fixing for Tabular Question Answering Evangelatos, Andreas Filandrianos, Giorgos Lymperaiou, Maria Voulodimos, Athanasios Stamou, Giorgos Computation and Language In this paper, we present our submission to SemEval-2025 Task 8: Question Answering over Tabular Data. This task, evaluated on the DataBench dataset, assesses Large Language Models' (LLMs) ability to answer natural language questions over structured data while addressing topic diversity and table size limitations in previous benchmarks. We propose a system that employs effective LLM prompting to translate natural language queries into executable code, enabling accurate responses, error correction, and interpretability. Our approach ranks first in both subtasks of the competition in the proprietary model category, significantly outperforming the organizer's baseline. |
| title | AILS-NTUA at SemEval-2025 Task 8: Language-to-Code prompting and Error Fixing for Tabular Question Answering |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2503.00435 |