An entropy-driven fusion of logits-based and sampling-based watermarks is claimed to outperform existing LLM watermarking methods on all four evaluation axes.
Title resolution pending
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
-
From Trade-off to Synergy: A Versatile Symbiotic Watermarking Framework for Large Language Models
An entropy-driven fusion of logits-based and sampling-based watermarks is claimed to outperform existing LLM watermarking methods on all four evaluation axes.