English(EN) Is Human-Like Text Liked by Humans? Multilingual Human Detection and Preference Against AI

研究发现，人类能以87.6%的准确率识别AI文本

作者 PulseAugur 编辑部 · [1 个来源] · 2026-04-30 04:00

一项新研究挑战了此前关于人类难以区分AI生成文本与人类写作的观点。研究人员发现，在九种语言和九个领域中，标注者能以87.6%的准确率识别AI文本。研究指出了具体性、文化细微差别和多样性方面的关键差异，尽管明确提示可以弥合一些差距。有趣的是，当来源不明确时，人类并不总是偏好人类写的文本。 AI

影响挑战了关于AI文本检测的假设，表明内容真实性验证可能得到改进。

排序理由关于人类检测AI生成文本的学术论文。

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Research; 关于人类检测AI生成文本的学术论文。
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 152 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.CL TIER_1 English(EN) · Yuxia Wang, Rui Xing, Jonibek Mansurov, Giovanni Puccetti, Zhuohan Xie, Minh Ngoc Ta, Jiahui Geng, Jinyan Su, Mervat Abassy, Saad El Dine Ahmed, Kareem Elozeiri, Nurkhan Laiyk, Maiya Goloburda, Tarek Mahmoud, Raj Vardhan Tomar, Alexander Aziz, Ryuto Koike · 2026-04-30 04:00

人类喜欢像人类写的文本吗？多语言人类检测与对AI的偏好

arXiv:2502.11614v3 Announce Type: replace Abstract: Prior studies have shown that distinguishing text generated by Large Language Models (LLMs) from human-written one is highly challenging for humans, and often no better than random guessing. To verify the generalizability of thi…