Goto

Collaborating Authors

 Government



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.





JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models

Neural Information Processing Systems

Jailbreak attacks cause large language models (LLMs) to generate harmful, unethical, or otherwise objectionable content. Evaluating these attacks presents a number of challenges, which the current collection of benchmarks and evaluation techniques do not adequately address.