R-CoT embeds watermarks into LLM reasoning paths via redundant CoT and GRPO-based dual optimization, maintaining over 95% true positive rate under fine-tuning and post-training changes.
Weda: Exploring copyright protec- tion for large language model downstream alignment
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
R-CoT: A Reasoning-Layer Watermark via Redundant Chain-of-Thought in Large Language Models
R-CoT embeds watermarks into LLM reasoning paths via redundant CoT and GRPO-based dual optimization, maintaining over 95% true positive rate under fine-tuning and post-training changes.