用大模型动态生成SQL，精准回答表格问答问题
Agentic LLMs for Question Answering over Tabular Data
- 通过多阶段流程：选例、生成SQL、验证与迭代优化
- 在DataBench上达70.5%准确率，远超26%基线
- 适合需要智能解析表格数据的开发者与研究者
表格问答（Table QA）因真实表格结构多样、规模不一、数据类型复杂而面临独特挑战。SemEval 2025 Task 8（DataBench）引入了一个大规模、跨领域数据集作为基准，用于评估模型处理结构化查询的能力。本文提出一种基于大语言模型（LLMs）的自然语言转SQL（NL-to-SQL）方法，使用GPT-4o、GPT-4o-mini和DeepSeek v2:16b等模型动态生成SQL查询。系统采用多阶段流水线：示例选择、SQL生成、答案提取、验证及迭代优化。实验表明，该方法在DataBench QA上达到70.5%准确率，在DataBench Lite QA上达71.6%，显著优于26%和27%的基线表现。本文详述方法细节、实验结果及替代方案，揭示了大模型驱动表格问答的优势与局限。
原文摘要 · Abstract (English)
Question Answering over Tabular Data (Table QA) presents unique challenges due to the diverse structure, size, and data types of real-world tables. The SemEval 2025 Task 8 (DataBench) introduced a benchmark composed of large-scale, domain-diverse datasets to evaluate the ability of models to accurately answer structured queries. We propose a Natural Language to SQL (NL-to-SQL) approach leveraging large language models (LLMs) such as GPT-4o, GPT-4o-mini, and DeepSeek v2:16b to generate SQL queries dynamically. Our system follows a multi-stage pipeline involving example selection, SQL query generation, answer extraction, verification, and iterative refinement. Experiments demonstrate the effectiveness of our approach, achieving 70.5\% accuracy on DataBench QA and 71.6\% on DataBench Lite QA, significantly surpassing baseline scores of 26\% and 27\% respectively. This paper details our methodology, experimental results, and alternative approaches, providing insights into the strengths and limitations of LLM-driven Table QA.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。