Normative conflicts and shallow AI alignment
Sign Up to like & getrecommendations! Published in 2025 at "Philosophical Studies"
DOI: 10.1007/s11098-025-02347-3
Abstract: The progress of AI systems such as large language models (LLMs) raises increasingly pressing concerns about their safe deployment. This paper examines the value alignment problem for LLMs, arguing that current alignment strategies are fundamentally… read more here.
Keywords: normative conflicts; conflicts shallow; psychology; language ... See more keywords