dorsal/arxiv
View SchemaDetecting LLM-Generated Text with Performance Guarantees
| Authors | Hongyi Zhou, Jin Zhu, Ying Yang, Chengchun Shi |
|---|---|
| Categories | |
| ArXiv ID | 2601.06586vv1 |
| URL | https://arxiv.org/abs/2601.06586 |
| License | http://creativecommons.org/licenses/by/4.0/ |
Abstract
Large language models (LLMs) such as GPT, Claude, Gemini, and Grok have been deeply integrated into our daily life. They now support a wide range of tasks -- from dialogue and email drafting to assisting with teaching and coding, serving as search engines, and much more. However, their ability to produce highly human-like text raises serious concerns, including the spread of fake news, the generation of misleading governmental reports, and academic misconduct. To address this practical problem, we train a classifier to determine whether a piece of text is authored by an LLM or a human. Our detector is deployed on an online CPU-based platform https://huggingface.co/spaces/stats-powered-ai/StatDetectLLM, and contains three novelties over existing detectors: (i) it does not rely on auxiliary information, such as watermarks or knowledge of the specific LLM used to generate the text; (ii) it more effectively distinguishes between human- and LLM-authored text; and (iii) it enables statistical inference, which is largely absent in the current literature. Empirically, our classifier achieves higher classification accuracy compared to existing detectors, while maintaining type-I error control, high statistical power, and computational efficiency.
{
"annotation_id": "643b504d-ff11-418f-98f0-8170553eadf2",
"date_created": "2026-02-17T05:53:08.815000Z",
"date_modified": "2026-02-17T05:53:08.815000Z",
"file_hash": "841e6b50bfd672dc705f55aabc38faf4f63ed85f67472a8d9eebf271a934cb4d",
"private": false,
"record": {
"abstract": "Large language models (LLMs) such as GPT, Claude, Gemini, and Grok have been deeply integrated into our daily life. They now support a wide range of tasks -- from dialogue and email drafting to assisting with teaching and coding, serving as search engines, and much more. However, their ability to produce highly human-like text raises serious concerns, including the spread of fake news, the generation of misleading governmental reports, and academic misconduct. To address this practical problem, we train a classifier to determine whether a piece of text is authored by an LLM or a human. Our detector is deployed on an online CPU-based platform https://huggingface.co/spaces/stats-powered-ai/StatDetectLLM, and contains three novelties over existing detectors: (i) it does not rely on auxiliary information, such as watermarks or knowledge of the specific LLM used to generate the text; (ii) it more effectively distinguishes between human- and LLM-authored text; and (iii) it enables statistical inference, which is largely absent in the current literature. Empirically, our classifier achieves higher classification accuracy compared to existing detectors, while maintaining type-I error control, high statistical power, and computational efficiency.",
"arxiv_id": "2601.06586",
"authors": [
"Hongyi Zhou",
"Jin Zhu",
"Ying Yang",
"Chengchun Shi"
],
"categories": [
"cs.CL",
"cs.LG",
"stat.AP",
"stat.ML"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"title": "Detecting LLM-Generated Text with Performance Guarantees",
"url": "https://arxiv.org/abs/2601.06586",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "44281831-d2cd-48f2-9177-de975ee25daa",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}