TableBench
收藏资源简介:
TableBench 数据集是一个专注于表格问答多维度能力的集合,涵盖了4个主要类别和18个子类别。数据集包括多个字段,如唯一标识符、问题类型、问题子类型、指令、指令类型、表格、问题、答案和答案格式化器。数据示例展示了如何在验证集中使用这些字段,并说明了如何根据特定的格式要求生成答案。数据集的使用说明提供了如何评估大型语言模型在表格数据上的能力,以及如何根据特定的格式要求进行自定义评估。
The TableBench dataset is a collection dedicated to the multi-dimensional capabilities of table-based question answering, encompassing 4 main categories and 18 subcategories. The dataset comprises multiple fields, including unique identifier, question type, question subtype, instruction, instruction type, table, question, answer, and answer formatter. Dataset examples illustrate how to utilize these fields in the validation set and demonstrate how to generate answers that meet specific formatting requirements. The dataset's usage guidelines provide instructions on evaluating the performance of Large Language Models (LLMs) on tabular data, as well as conducting custom evaluations tailored to specific formatting standards.
数据集卡片 - TableBench
数据集概述
TableBench 是一个数据集,涵盖 4 个主要类别和 18 个子类别,专注于表格问答的多维度能力。
数据字段
| ID | 字段 | 描述 |
|---|---|---|
| id | 字符串 | 唯一标识符 |
| qtype | 字符串 | 问题类型(FactChecking, NumericalReasoning, DataAnalysis, Visualization) |
| qsubtype | 字符串 | 问题子类型 |
| instruction | 字符串 | 提示LLM的指令 |
| instruction_type | 字符串 | TableBench中的三种不同指令类型:TCoT(文本思维链)、SCoT(符号思维链)和PoT(思维程序) |
| table | 字符串 | 表格 |
| question | 字符串 | 问题 |
| answer | 字符串 | 答案 |
| answer_formatter | 字符串 | 答案输出格式的约束 |
数据示例
一个 validation 示例如下: json { "id": "60670a8d9b1e39dd845fb1639d0d8b86", "qtype": "DataAnalysis", "qsubtype": "StatisticalAnalysis", "instruction": "You are a data analyst proficient in Python ...", "instruction_type": "PoT", "table": "{"columns": ["rank", "circuit", "headquarters", "screens", "sites"], "data": [[1, "regal entertainment group", "knoxville , tn", 7367, 580], [2, "amc entertainment inc", "kansas city , mo", 5894, 483], [3, "cinemark theatres", "plano , tx", 3895, 298], [4, "carmike cinemas , inc", "columbus , ga", 2242, 232], [5, "cineplex entertainment", "toronto , on", 1438, 133], [6, "rave motion pictures", "dallas , tx", 939, 62], [7, "marcus theatres", "milwaukee , wi", 687, 55], [8, "national amusements", "dedham , ma", 450, 34], [9, "empire theatres", "stellarton , ns", 438, 53]]}", "question": "Can you calculate the standard deviation of the number of screens operated by the top 5 movie theater chains?", "answer": "2472.33", "answer_formatter": "The generated Python code should follow the format below, and ensure the first two code lines is exactly the same with the following code block: [Python Code Format] python import pandas as pd df = pd.read_csv(table.csv) ... print(fFinal Answer: {answer})
Ensure the final answer is the last line in python code and can only be in the "print(fFinal Answer: {answer})" form, no other from. Ensure variable "answer" can only be "AnswerName1, AnswerName2..." form, no other form, and "AnswerName" can only be a number or entity name, as short as possible, without any explanation." }
数据使用
- 如果你想直接评估LLMs在表格数据上的能力,可以使用
TableBench-PoT、TableBench-SCoT和TableBench-TCoT直接评估模型的能力。 - 如果你希望自定义评估提示方法,请遵循
answer_formatter中的规范,以减少因自由形式答案不一致导致的评估错误。




