REVIEW 4 cited by
Three Bricks to Consolidate Watermarks for Large Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
abstract
The task of discerning between generated and natural texts is increasingly challenging. In this context, watermarking emerges as a promising technique for ascribing generated text to a specific model. It alters the sampling generation process so as to leave an invisible trace in the generated output, facilitating later detection. This research consolidates watermarks for large language models based on three theoretical and empirical considerations. First, we introduce new statistical tests that offer robust theoretical guarantees which remain valid even at low false-positive rates (less than 10$^{\text{-6}}$). Second, we compare the effectiveness of watermarks using classical benchmarks in the field of natural language processing, gaining insights into their real-world applicability. Third, we develop advanced detection schemes for scenarios where access to the LLM is available, as well as multi-bit watermarking.
Forward citations
Cited by 4 Pith papers
-
Beyond Heuristic Tuning: Power-Calibrated LLM Watermarking
A power-calibrated statistical framework gives closed-form links from KGW watermark parameters (γ, δ) to detection power and KL distortion, enabling principled Pareto-optimal selection.
-
Debiasing Watermarks for Large Language Models via Maximal Coupling
A new LLM watermarking scheme uses maximal coupling to embed a detectable signal while keeping the generated token distribution exactly unbiased.
-
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.
-
Temperature Matters: Enhancing Watermark Robustness Against Paraphrasing Attacks
A watermark that seeds each token's sampling temperature from a hash of the previous h tokens is claimed to beat the Aaronson watermark under a 30% BERT paraphrase attack, based on a single ROC curve without error bars.
Discussion (0). Continue with ORCID to comment.