Search Results for author:
Found 3 papers, 1 papers with code
ConTrans: Weak-to-Strong Alignment Engineering via Concept Transplantation
From the perspective of representation engineering, ConTrans refines concept vectors in value alignment from a source LLM (usually a weak yet aligned LLM).
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.
Language Representation Projection: Can We Transfer Factual Knowledge across Languages in Multilingual Language Models?
Multilingual pretrained language models serve as repositories of multilingual factual knowledge.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
