AH&AITD – Arslan’s Human and AI Text Database
收藏资源简介：
AH&AITD is a comprehensive benchmark dataset designed to support the evaluation of AI-generated text detection tools. The dataset contains <b>11,580 samples</b> spanning both <b>human-written</b> and <b>AI-generated</b> content across multiple domains. It was developed to address limitations in previous datasets, particularly in terms of diversity, scale, and real-world applicability. To facilitate research in the detection of AI-generated text by providing a diverse, multi-domain dataset. This dataset enables fair benchmarking of detection tools across various writing styles and content categories.<b>Composition</b><b>1. Human-Written Samples (Total: 5,790)</b>Collected from:<b>Open Web Text</b> (2,343 samples)<b>Blogs</b> (196 samples)<b>Web Text</b> (397 samples)<b>Q&A Platforms</b> (670 samples)<b>News Articles</b> (430 samples)<b>Opinion Statements</b> (1,549 samples)<b>Scientific Research Abstracts</b> (205 samples)<b>2. AI-Generated Samples (Total: 5,790)</b>Generated using:<b>ChatGPT</b> (1,130 samples)<b>GPT-4</b> (744 samples)<b>Paraphrase Models</b> (1,694 samples)<b>GPT-2</b> (328 samples)<b>GPT-3</b> (296 samples)<b>DaVinci (GPT-3.5 variant)</b> (433 samples)<b>GPT-3.5</b> (364 samples)<b>OPT-IML</b> (406 samples)<b>Flan-T5</b> (395 samples)<b>Citation:</b>Akram, A. (2023). <i>AH&AITD: Arslan’s Human and AI Text Database</i>. [Dataset]. Associated with the article: <i>An Empirical Study of AI-Generated Text Detection Tools</i>. Advances in Machine Learning & Artificial Intelligence, 4(2), 44–55.
**AH&AITD** 是一款用于支撑AI生成文本检测工具（AI-generated text detection tools）评估的综合性基准数据集（benchmark dataset）。该数据集包含**11580条样本**，覆盖多领域的**人工撰写文本**与**AI生成文本**。其研发初衷旨在弥补过往数据集在多样性、规模与实际应用适配性方面的短板，通过提供多样化多领域数据集以推动AI生成文本检测领域的研究。本数据集可实现不同写作风格与内容类别下的检测工具公平基准评测。 **数据集构成** 1. **人工撰写样本（总计5790条）** 采集来源如下： - 开放网络文本（Open Web Text）：2343条 - 博客（Blogs）：196条 - 网页文本（Web Text）：397条 - 问答平台（Q&A Platforms）：670条 - 新闻稿件（News Articles）：430条 - 观点陈述（Opinion Statements）：1549条 - 科研摘要（Scientific Research Abstracts）：205条 2. **AI生成样本（总计5790条）** 生成模型如下： - ChatGPT：1130条 - GPT-4：744条 - 复述模型（Paraphrase Models）：1694条 - GPT-2：328条 - GPT-3：296条 - DaVinci（GPT-3.5变体）：433条 - GPT-3.5：364条 - OPT-IML：406条 - Flan-T5：395条 **引用信息** Akram, A. (2023). *AH&AITD: Arslan’s Human and AI Text Database* [数据集]. 关联论文：*An Empirical Study of AI-Generated Text Detection Tools*，《Advances in Machine Learning & Artificial Intelligence》，4(2)，44–55.
