作者位次 #5/8ACL 2026Poster· Natural Language Processing
R eas M ark: A Robust Watermark for Attributing LLM Reasoning Under Knowledge Distillation Attacks
Peizhuo Lv · Ruihua Zhou · Yunpeng Li · Ruigang Liang · Xingshuo Han · XiaoFeng Wang · Wei Dong · Yuling Liu
摘要
Reasoning-enhanced large language models rely on intermediate reasoning signals to solve complex, multi-step tasks, making reasoning behavior a valuable form of intellectual property. Meanwhile, knowledge distillation enables an adversary to replicate this behavior in a realistic black-box settin...