TART让大模型更懂表格数据，提升推理准确性和可解释性。
TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning
- 用工具增强大模型，精准处理表格数据
- 在新数据集上达到90% GPT-3.5-turbo的准确率
- 开源框架适合需要可解释推理的研究者
当前大型语言模型在理解表格结构和执行精确数值推理方面能力有限，这对表格问答（TQA）和基于表格的事实验证（TFV）任务至关重要。为此，我们提出表格工具增强推理框架TART，整合大模型与专用工具。TART包含三个核心组件：表格格式化器确保数据准确呈现，工具构建器开发特定计算工具，解释生成器保障推理过程可解释性。我们还构建了TOOLTAB数据集，专用于训练大模型进行表格-工具融合。实验表明，TART相比现有方法（如思维链）在数据处理精度和推理清晰度上均有显著提升。值得注意的是，TART结合CodeLlama实现了90.0%的准确率，接近闭源模型GPT-3.5-turbo水平，展现出在多样真实场景中的鲁棒性。所有代码与数据已开源至https://github.com/XinyuanLu00/TART。
原文摘要 · Abstract (English)
Current Large Language Models (LLMs) exhibit limited ability to understand table structures and to apply precise numerical reasoning, which is crucial for tasks such as table question answering (TQA) and table-based fact verification (TFV). To address these challenges, we introduce our Tool-Augmented Reasoning framework for Tables (TART), which integrates LLMs with specialized tools. TART contains three key components: a table formatter to ensure accurate data representation, a tool maker to develop specific computational tools, and an explanation generator to maintain explainability. We also present the TOOLTAB dataset, a new benchmark designed specifically for training LLMs in table-tool integration. Our experiments indicate that TART achieves substantial improvements over existing methods (e.g., Chain-of-Thought) by improving both the precision of data processing and the clarity of the reasoning process. Notably, TART paired with CodeLlama achieves 90.0% of the accuracy of the closed-sourced LLM GPT-3.5-turbo, highlighting its robustness in diverse real-world scenarios. All the code and data are available at https://github.com/XinyuanLu00/TART.
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。