Goto

Collaborating Authors

 Deep Learning



Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature

Neural Information Processing Systems

Text watermarks for large language models (LLMs) have been commonly used to identify the origins of machine-generated content, which is promising for assessing liability when combating deepfake or harmful content.


A Proof of Theorem 4.1

Neural Information Processing Systems

After this process, we utilize the official PyTorch implementation of Meng et al.




WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models

Neural Information Processing Systems

Despite growing interest, much of the existing research has focused on varied unlearning method designs to boost effectiveness and efficiency. However, the inherent relationship between model weights and LLM unlearning has not been extensively examined.