作者位次 #2/4ACL 2026Poster· Natural Language Processing
A Linguistics-Aware LLM Watermarking via Syntactic Predictability
Shinwoo Park · Hyejin Park · Hyeseon An · Yo-Sub Han
摘要
As large language models (LLMs) continue to advance rapidly, reliable governance tools have become critical. Publicly verifiable watermarking is particularly essential for fostering a trustworthy AI ecosystem. A central challenge persists: balancing text quality against detection robustness. Rece...