ToolQA

该数据集名为ToolQA，包含了来自8个不同领域的数据，每个实例都是由（问题、答案、参考语料库以及工具）组成的元组，旨在评估大型语言模型在利用外部工具进行问答方面的能力。为了减少与大型语言模型预训练数据之间的重叠，ToolQA还特别包含了13个专门工具，用于包括文本检索、数据库操作以及数学计算在内的各种操作。该任务的目的是使用外部工具进行问题解答。

This dataset, named ToolQA, contains data from 8 distinct domains. Each instance is a tuple composed of a question, an answer, a reference corpus, and a tool, which is designed to evaluate the capabilities of large language models (LLMs) in performing question answering with external tool assistance. To minimize overlap with the pre-training data of large language models, ToolQA specifically incorporates 13 specialized tools for various operations including text retrieval, database manipulation, and mathematical calculation. The objective of this task is to answer questions by utilizing external tools.