✳flâneur — a map of the web's best reading

[2310.13798] Specific versus General Principles for Constitutional AI

arxiv.org · 741 words · saved by 1 readers

Abstract:Human feedback can prevent overtly harmful utterances in conversational models, but may not automatically mitigate subtle problematic behaviors such as a stated desire for self-preservation or power. Constitutional AI offers an alternative, replacing human feedback with feedback from AI models conditioned only on a list of written principles. We find this approach effectively prevents the expression of such behaviors. The success of simple principles motivates us to ask: can models learn general ethical behaviors from only a single written principle? To test this, we run experiments using a principle roughly stated as "do what's best for humanity". We find that the largest dialogue models can generalize from this short constitution, resulting in harmless assistants with no stated interest in specific motivations like power. A general principle may thus partially avoid the need for a long list of constitutions targeting potentially harmful behaviors. However, more detailed constitutions still improve fine-grained control over specific types of harms. This suggests both general and specific principles have value for steering AI safely.

[2310.13798] Specific versus General Principles for Constitutional AI Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Computation and Language arXiv:2310.13798 (cs) [Submitted on 20 Oct 2023] Title: Specific versus General Principles for Constitutional AI Authors: Sandipan Kundu , Yuntao Bai , Saurav Kadavath , Amanda Askell , Andrew Callahan , Anna Chen , Anna Goldie , Avital Balwit , Azalia Mirhoseini , Brayden McLean , Catherine Olsson , Cassie Evraets , Eli Tran-Johnson , Esin

Explore this link on the map →

related reading