A trigger-based watermark for multi-agent reasoning traces detects only the injected phrase, not the reproduction of copyrighted content.
Claude: A family of language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
CoTGuard: Using Chain-of-Thought Triggering for Copyright Protection in Multi-Agent LLM Systems
A trigger-based watermark for multi-agent reasoning traces detects only the injected phrase, not the reproduction of copyrighted content.