作者位次 #4/9ACL 2026Poster· Natural Language Processing
Verifiable LLM -Generated Text Detection via Projected Semantic-Structural Distributions
Ruochong Xiong · Qien Li · Wangwang Lian · Yulong Wan · Hanlin Xue · Zhouxing Tan · Han Yang · Fengyu Lu · Junfei Liu
摘要
The widespread deployment of large language models (LLMs) makes detecting LLM-Generated text a critical security task. Existing methods, primarily relying on output probabilities from proxy models or single semantic features, suffer from distribution misalignment and limited interpretability. We...