Team Anotheroption at SemEval-2025 Task 8: Bridging the Gap Between Open-Source and Proprietary LLMs in Table QA
This work addresses the challenge of improving open-source models to match proprietary LLMs in table QA, representing an incremental advancement in a specific domain.
The paper tackled the problem of question answering over tabular data by developing a system that integrates text-to-SQL, text-to-code, self-correction, retrieval-augmented generation, and an end-to-end module, achieving 80% accuracy and a top-13 ranking among 38 teams in SemEval-2025 Task 8.
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.