Are language models rational? The case of coherence norms and belief revision

Understand

Do norms of rationality apply to machine learning models, in particular language models? In this paper we investigate this question by focusing on a special subset of rational norms: coherence norms.

• We consider both logical coherence norms as well as coherence norms tied to the strength of belief.
• To make sense of the latter, we introduce the Minimal Assent Connection (MAC) and propose a new account of credence, which captures the strength of belief in language models.
• This proposal uniformly assigns strength of belief simply on the basis of model internal next token probabilities.