A topic-guided watermarking scheme partitions the LLM vocabulary into topic-aligned token subsets and green-lists relevant tokens based on the input prompt to embed detectable marks while preserving text quality and improving robustness to attacks.
TLDR : Extreme Summarization of Scientific Documents
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Vocabulary adaptation via targeted token addition and replacement improves semantic similarity, domain word usage, and training efficiency for LLM summarization in legal and medical domains.
citing papers explorer
-
Topic-Based Watermarks for Large Language Models
A topic-guided watermarking scheme partitions the LLM vocabulary into topic-aligned token subsets and green-lists relevant tokens based on the input prompt to embed detectable marks while preserving text quality and improving robustness to attacks.
-
Learning Faster with Better Tokens: Parameter-Efficient Vocabulary Adaptation for Specialized Text Summarization
Vocabulary adaptation via targeted token addition and replacement improves semantic similarity, domain word usage, and training efficiency for LLM summarization in legal and medical domains.