ReTokSync resolves tokenization ambiguity in generative linguistic steganography via targeted self-synchronizing resets, achieving over 99.7% extraction accuracy and 100% recovery with an auxiliary channel while matching baseline security and quality.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
VAC replaces scalar rewards with natural language feedback in an alternating training loop between a feedback model and a policy model, yielding better personalized QA on the LaMP-QA benchmark.
citing papers explorer
-
ReTokSync: Self-Synchronizing Tokenization Disambiguation for Generative Linguistic Steganography
ReTokSync resolves tokenization ambiguity in generative linguistic steganography via targeted self-synchronizing resets, achieving over 99.7% extraction accuracy and 100% recovery with an auxiliary channel while matching baseline security and quality.
-
Learning from Natural Language Feedback for Personalized Question Answering
VAC replaces scalar rewards with natural language feedback in an alternating training loop between a feedback model and a policy model, yielding better personalized QA on the LaMP-QA benchmark.