首页/数据集/Blinded assessment of the readability of ChatGPT-generated vs original abstracts.

Blinded assessment of the readability of ChatGPT-generated vs original abstracts.

NIAID Data Ecosystem2026-05-01 收录

数据链接：

https://figshare.com/articles/dataset/Blinded_assessment_of_the_readability_of_ChatGPT-generated_vs_original_abstracts_/25220141 数据链接链接失效反馈

官方服务：

资源简介：

Blinded assessment of the readability of ChatGPT-generated vs original abstracts.

应用场景：

创建时间：

2024-02-14

文本可读性评估

自然语言处理

Readability tools and their interpretations.

Figshare2019-06-20 更新320

Estimated time saving by generative AI use worldwide 2025, by task

生成式AI评估

任务时间节省预测

Estimated impact of the use of generative artificial intelligence (AI) on the time spent in organizations' roles worldwide in 2025, by task

Statista70

On the readability of texts presented in sentence-by-sentence segments to beginner readers: Evidence from self-paced reading and eye tracking

文本可读性评估

眼动阅读行为

This DataVerseNL Publication package contains the raw and processed data files, R-markdown scripts, Ibex-farm and Eyelink 1000 presentation scripts, stimuli files. ethical approval files etc. related

DataCite Commons2025-07-03 更新50

OmniPhys

生成式AI评估

物理常识基准

OmniPhys是由浙江大学等机构联合构建的物理常识基准数据集，旨在系统评估文本到图像生成模型的物理合理性。该数据集包含1551个精心设计的样本，覆盖力学、光学和物体属性三大领域，基于物理知识图谱（PKG）和PhET模拟构建，确保每个样本均对应可视觉验证的物理知识节点。数据集通过隐式查询和双路径验证协议，诊断模型对基础物理定律的内化理解，而非表面模式匹配，主要应用于提升生成式AI的物理对齐能力，解

arXiv2026-07-28 更新220

Open-Ended Scrum Framework Questions in a Software Engineering Course

敏捷开发评估

生成式AI评估

This dataset is used for the automated assessment of open-ended exam questions in the online course Introduction to Software Engineering at Constantine the Philosopher University in Nitra. The dataset

IEEE70

Blinded assessment of the readability of ChatGPT-generated vs original abstracts.

资源简介：

相关数据集