TSM-Bench: Detecting LLM-Generated Text in Real-World Wikipedia Editing Practices 事件

PRODUCT_LAUNCH2026-06-01影响: MEDIUM

TSM-Bench: Detecting LLM-Generated Text in Real-World Wikipedia Editing Practices arXiv:2605.31113v1 Announce Type: new Abstract: Automatically detecting machine-generated text (MGT) is critical to maintaining the knowledge integrity of user-generated content (UGC) platforms such as Wikipedia. Existing detection benchmarks primarily focus on \textit{generic} text generation tasks (e.g., ``Write an article about machine learning.''). However, editors frequently employ LLMs for specific writing t

TSM-Bench: Detecting LLM-Generated Text in Real-World Wikipedia Editing Practices · 相关公司

W
World LabsRESEARCH_INSTITUTE
W
WikipediaNONPROFIT
A
arXivNONPROFIT
G
GLENONPROFIT
H
HuMANONPROFIT
E
EARNNONPROFIT
A
ACTNONPROFIT
R
RatioRESEARCH_INSTITUTE