零样本生成代码解决表格问答，无需微调即达前列。
LyS at SemEval 2025 Task 8: Zero-Shot Code Generation for Tabular QA
- 用大模型直接生成代码提取表格信息，分步优化列选择与类型分析。
- 零样本下排名33/53，证明无需微调也能有效完成表格问答。
- 支持错误迭代修正，提升代码生成鲁棒性，适合低资源场景。
本文介绍我们在 SemEval 2025 任务8（表格问答）中的参与情况。我们提出一个零样本流水线，利用大语言模型生成可执行代码，从表格数据中提取问题相关的信息。该方法采用模块化设计，主代码生成模块结合列筛选与数据类型分析组件，以提升提取准确率。当生成代码失败时，触发迭代优化流程，将错误反馈融入新提示，增强系统鲁棒性。实验结果表明，零样本代码生成在无任务特定微调的情况下仍具可行性，在测试阶段取得 33/53 的排名。
原文摘要 · Abstract (English)
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.
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。