Probabilistic coherence, logical consistency, and Bayesian learning: Neural language models as epistemic agents.

ABSTRACT: It is argued that suitably trained neural language models exhibit key properties of epistemic agency: they hold probabilistically coherent and logically consistent degrees of belief, which they can rationally revise in the face of novel evidence. To this purpose, we conduct computational experiments with rankers: T5 models [Raffel et al. 2020] that are pretrained on carefully designed synthetic corpora. Moreover, we introduce a procedure for eliciting a model's degrees of belief, and define numerical metrics that measure the extent to which given degrees of belief violate (probabilistic, logical, and Bayesian) rationality constraints. While pretrained rankers are found to suffer from global inconsistency (in agreement with, e.g., [Jang et al. 2021]), we observe that subsequent self-trainin

SUBMITTER: Betz G 

PROVIDER: S-EPMC9910757 | biostudies-literature | 2023

REPOSITORIES: biostudies-literature