# LyS at SemEval 2025 Task 8: Zero-Shot Code Generation for Tabular QA

Source: [LyS at SemEval 2025 Task 8: Zero-Shot Code Generation for Tabular QA](<https://www.sota2.com/research/paper/68fa7a971e209131cea841be>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:23:58.707Z

Authors: Adri\\'an Gude, Roi Santos-R\\'ios, Francisco Prado-Vali\\~no, Ana Ezquerro, Jes\\'us Vilares

Published: 2025-08-12T15:25:31.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.09012>)

[PDF](<https://arxiv.org/pdf/2508.09012.pdf>)
