The authors give constructions for provably undetectable watermarking of constant-entropy LLM outputs that are robust to random substitutions (under subexponential LPN) and to substitutions plus random deletions (under an additional heuristic or pseudorandom ECC).
Edit distance robust watermarks for language models.CoRR, abs/2406.02633
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
-
Can we Watermark Low-Entropy LLM Outputs?
The authors give constructions for provably undetectable watermarking of constant-entropy LLM outputs that are robust to random substitutions (under subexponential LPN) and to substitutions plus random deletions (under an additional heuristic or pseudorandom ECC).