People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Russell, Jenna, Karpinska, Marzena, Iyyer, Mohit
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913847648976896
author Russell, Jenna
Karpinska, Marzena
Iyyer, Mohit
author_facet Russell, Jenna
Karpinska, Marzena
Iyyer, Mohit
contents In this paper, we study how well humans can detect text generated by commercial LLMs (GPT-4o, Claude, o1). We hire annotators to read 300 non-fiction English articles, label them as either human-written or AI-generated, and provide paragraph-length explanations for their decisions. Our experiments show that annotators who frequently use LLMs for writing tasks excel at detecting AI-generated text, even without any specialized training or feedback. In fact, the majority vote among five such "expert" annotators misclassifies only 1 of 300 articles, significantly outperforming most commercial and open-source detectors we evaluated even in the presence of evasion tactics like paraphrasing and humanization. Qualitative analysis of the experts' free-form explanations shows that while they rely heavily on specific lexical clues ('AI vocabulary'), they also pick up on more complex phenomena within the text (e.g., formality, originality, clarity) that are challenging to assess for automatic detectors. We release our annotated dataset and code to spur future research into both human and automated detection of AI-generated text.
format Preprint
id arxiv_https___arxiv_org_abs_2501_15654
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text
Russell, Jenna
Karpinska, Marzena
Iyyer, Mohit
Computation and Language
Artificial Intelligence
In this paper, we study how well humans can detect text generated by commercial LLMs (GPT-4o, Claude, o1). We hire annotators to read 300 non-fiction English articles, label them as either human-written or AI-generated, and provide paragraph-length explanations for their decisions. Our experiments show that annotators who frequently use LLMs for writing tasks excel at detecting AI-generated text, even without any specialized training or feedback. In fact, the majority vote among five such "expert" annotators misclassifies only 1 of 300 articles, significantly outperforming most commercial and open-source detectors we evaluated even in the presence of evasion tactics like paraphrasing and humanization. Qualitative analysis of the experts' free-form explanations shows that while they rely heavily on specific lexical clues ('AI vocabulary'), they also pick up on more complex phenomena within the text (e.g., formality, originality, clarity) that are challenging to assess for automatic detectors. We release our annotated dataset and code to spur future research into both human and automated detection of AI-generated text.
title People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2501.15654