Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Agrawal, Srishti Shekhar"'
LLMs are increasingly fine-tuned using RLHF datasets to align them with human preferences and values. However, very limited research has investigated which specific human values are operationalized through these datasets. In this paper, we introduce
Externí odkaz:
http://arxiv.org/abs/2411.11937
Publikováno v:
ACM SIGACCESS Conference on Computers & Accessibility; 2023, p1-5, 5p
