Cargando…

Judgment aggregation, discursive dilemma and reflective equilibrium: Neural language models as self-improving doxastic agents

Neural language models (NLMs) are susceptible to producing inconsistent output. This paper proposes a new diagnosis as well as a novel remedy for NLMs' incoherence. We train NLMs on synthetic text corpora that are created by simulating text production in a society. For diagnostic purposes, we e...

Descripción completa

Detalles Bibliográficos
Autores principales: Betz, Gregor, Richardson, Kyle
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9623417/
https://www.ncbi.nlm.nih.gov/pubmed/36329681
http://dx.doi.org/10.3389/frai.2022.900943