Papers with low-entropy scenarios

2 papers
Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods to watermark low-entropy content are expensive and risky . IE reduces parameter size by 99% while achieving performance on par with state-of-the-art methods .
Approach: They propose a logit-based watermarking paradigm that uses entropy-based features to predict whether the next token is high or low.
Outcome: The proposed method reduces parameter size by 99% while achieving performance on par with state-of-the-art methods.
An Entropy-based Text Watermarking Detection Method (2024.acl-long)

Copied to clipboard

Challenge: Existing text watermarking algorithms for large language models (LLMs) are effective in identifying machine-generated texts, but they are not effective in low-entropy scenarios.
Approach: They propose an Entropy-based text watermarking detection method that takes into account the influence of token entropy to better reflect the degree of watermark detection.
Outcome: The proposed method is training-free and fully automated.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations