作者位次 #2/7ACL 2026Poster· Natural Language Processing
UMPIRE : Unveiling LLM -generated Posts via Redundant Expressions
xiaoquan Yi · Haixing Wu · Haozhao Wang · Yichen Li · Yuhua Li · Rui Zhang · Ruixuan Li
摘要
The proliferation of Large Language Models (LLMs) has saturated social media platforms with hyper-realistic posts, rendering traditional detection methods that rely on low-level artifacts or unimodal statistics increasingly ineffective. In this work, we identify a fundamental semantic distinction...