AILS-NTUA at SemEval-2025 Task 8: Language-to-Code prompting and Error Fixing for Tabular Question Answering

Andreas Evangelatos, Giorgos Filandrianos, Maria Lymperaiou, Athanasios Voulodimos, Giorgos Stamou
3/1/2025
cs.CL

No official code found. Best implementation: andrewevag/tabularqa (3 stars, last commit 2025-05-02).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

andrewevag/tabularqaCommunity100%

Question Answering over Tabular Data with LLM Code Generation

32PythonFeb 27, 20251 years ago

Similar Papers

Team Anotheroption at SemEval-2025 Task 8: Bridging the Gap Between Open-Source and Proprietary LLMs in Table QA

88% match1 repo22025

ITUNLP at SemEval-2025 Task 8: Question-Answering over Tabular Data: A Zero-Shot Approach using LLM-Driven Code Generation

87% match2025

Agentic LLMs for Question Answering over Tabular Data

87% match2025

Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation

87% match2025

TableBench: A Comprehensive and Complex Benchmark for Table Question Answering

87% match1 repo932024

ReasonTabQA: A Comprehensive Benchmark for Table Question Answering from Real World Industrial Scenarios

84% match2026

Cite this paper

@article{evangelatos2025ailsntua,
  title  = {AILS-NTUA at SemEval-2025 Task 8: Language-to-Code prompting and Error Fixing for Tabular Question Answering},
  author = {Andreas Evangelatos and Giorgos Filandrianos and Maria Lymperaiou and Athanasios Voulodimos and Giorgos Stamou},
  year   = {2025},
  eprint = {2503.00435},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2503.00435v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2503.00435.svg)](https://codeofpaper.com/paper/2503.00435)

Discussion