HIGHLIGHTS
- who: Atoosa Kasirzadeh from the University of Edinburgh, Edinburgh, UK have published the research: In Conversation with Artificial Intelligence: Aligning language Models with Human Values, in the Journal: (JOURNAL)
- what: The authors propose a number of steps that help answer these questions. The authors explore how these norms can be used to align conversational agents with human values across a range of different discursive domains. This approach seeks to specify more precisely what ideal linguistic communication is, across a range of contexts, and to realise these properties in the design of conversational agents . To answer . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.