Search Results for author:
Found 2 papers, 0 papers with code
PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference
In this work, we introduce the PKU-SafeRLHF dataset, designed to promote research on safety alignment in large language models (LLMs).
Aligner: Efficient Alignment by Learning to Correct
However, the tension between the complexity of current alignment methods and the need for rapid iteration in deployment scenarios necessitates the development of a model-agnostic alignment approach that can operate under these constraints.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
