Search Results for author:
Found 6 papers, 2 papers with code
Exploring Multilingual Concepts of Human Value in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?
Drawing from our findings on multilingual value alignment, we prudently provide suggestions on the composition of multilingual data for LLMs pre-training: including a limited number of dominant languages for cross-lingual alignment transfer while avoiding their excessive prevalence, and keeping a balanced distribution of non-dominant languages.
DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models
The ability of data memorization and regurgitation in pretrained language models, revealed in previous studies, brings the risk of data leakage.
Large Language Model Alignment: A Survey
We also envision bridging the gap between the AI alignment research community and the researchers engrossed in the capability exploration of LLMs for both capable and safe LLMs.
Swing Distillation: A Privacy-Preserving Knowledge Distillation Framework
Knowledge distillation (KD) has been widely used for model compression and knowledge transfer.
FewFedWeight: Few-shot Federated Learning Framework across Multiple NLP Tasks
It broadcasts the global model in the server to each client and produces pseudo data for clients so that knowledge from the global model can be explored to enhance few-shot learning of each client model.
Action Unit Detection with Joint Adaptive Attention and Graph Relation
This paper describes an approach to the facial action unit (AU) detection.
