Language models cannot reliably distinguish belief from knowledge and fact
https://www.nature.com/articles/s42256-025-01113-8
"[...] We also find that, while recent models show competence in recursive
knowledge tasks, they still rely on inconsistent reasoning strategies,
suggesting superficial pattern matching rather than robust epistemic
understanding. Most models lack a robust understanding of the factive
nature of knowledge, that knowledge inherently requires truth. These
limitations necessitate urgent improvements before deploying LMs in
high-stakes domains where epistemic distinctions are crucial."


[]s, JM

-- 
https://sites.google.com/site/sequiturquodlibet/

-- 
LOGICA-L
Lista acadêmica brasileira dos profissionais e estudantes da área de Lógica 
<[email protected]>
--- 
Você está recebendo esta mensagem porque se inscreveu no grupo "LOGICA-L" dos 
Grupos do Google.
Para cancelar inscrição nesse grupo e parar de receber e-mails dele, envie um 
e-mail para [email protected].
Para ver esta conversa, acesse 
https://groups.google.com/a/dimap.ufrn.br/d/msgid/logica-l/CAO6j_Lix0nmXxuXG1MSrY%2Bdiob92WzKsJ9B1djvMH6cscAE3RQ%40mail.gmail.com.

Responder a