Exploring Multilingual Concepts of Human Value in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?

28 February 2024

Papers citing "Exploring Multilingual Concepts of Human Value in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?"

4 / 4 papers shown

Title
ConTrans: Weak-to-Strong Alignment Engineering via Concept Transplantation Weilong Dong Xinwei Wu Renren Jin Shaoyang Xu Deyi Xiong 41 6 0 31 Dec 2024
Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems Tianyu Cui Yanling Wang Chuanpu Fu Yong Xiao Sijia Li ... Junwu Xiong Xinyu Kong Zujie Wen Ke Xu Qi Li 35 22 0 11 Jan 2024
Language Representation Projection: Can We Transfer Factual Knowledge across Languages in Multilingual Language Models? Shaoyang Xu Junzhuo Li Deyi Xiong KELM 35 6 0 07 Nov 2023
Systematic Inequalities in Language Technology Performance across the World's Languages Damián E. Blasi Antonios Anastasopoulos Graham Neubig 98 104 0 13 Oct 2021