用多步代码生成法，让大模型读懂西班牙语表格并准确回答问题。
MRT at IberLEF-2025 PRESTA Task: Maximizing Recovery from Tables with Multiple Steps
- 分步执行：解析表格、选列、生成自然语言指令并转为代码运行。
- 在IberLEF 2025任务中达到85%准确率，优于前一版本。
- 适合需要高精度表格问答的NLP研究者和开发者参考。
本文介绍我们在IberLEF 2025 PRESTA任务（西班牙语表格问答）中的解决方案。通过使用大语言模型生成Python代码，对表格进行过滤与处理，实现问题求解。该方法源自Semeval 2025相关任务的MRT实现，包含多个步骤：分析表格内容、选择有效列、生成自然语言指令、将指令转换为代码、执行代码，并处理潜在错误。每个步骤均采用开源大模型与细粒度优化提示词。最终在任务中取得85%的准确率。
原文摘要 · Abstract (English)
This paper presents our approach for the IberLEF 2025 Task PRESTA: Preguntas y Respuestas sobre Tablas en Español (Questions and Answers about Tables in Spanish). Our solution obtains answers to the questions by implementing Python code generation with LLMs that is used to filter and process the table. This solution evolves from the MRT implementation for the Semeval 2025 related task. The process consists of multiple steps: analyzing and understanding the content of the table, selecting the useful columns, generating instructions in natural language, translating these instructions to code, running it, and handling potential errors or exceptions. These steps use open-source LLMs and fine-grained optimized prompts for each step. With this approach, we achieved an accuracy score of 85\% in the task.
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。