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

TL;DR

This paper introduces a comprehensive system for table question answering that combines multiple LLM-based modules, achieving high accuracy and bridging the performance gap between open-source and proprietary models.

Contribution

It presents an integrated pipeline with text-to-SQL, text-to-code, self-correction, and retrieval-augmented generation modules, demonstrating improved accuracy in table QA tasks.

Findings

Achieved 80% accuracy in SemEval 2025 Task 8

Top-13 ranking among 38 teams

Significant accuracy improvement for open-source models

Abstract

This paper presents a system developed for SemEval 2025 Task 8: Question Answering (QA) over tabular data. Our approach integrates several key components: text-to-SQL and text-to-code generation modules, a self-correction mechanism, and a retrieval-augmented generation (RAG). Additionally, it includes an end-to-end (E2E) module, all orchestrated by a large language model (LLM). Through ablation studies, we analyzed the effects of different parts of our pipeline and identified the challenges that are still present in this field. During the evaluation phase of the competition, our solution achieved an accuracy of 80%, resulting in a top-13 ranking among the 38 participating teams. Our pipeline demonstrates a significant improvement in accuracy for open-source models and achieves a performance comparable to proprietary LLMs in QA tasks over tables. The code is available at GitHub repository.