Reposted by Zentrum für Demokratie Aarau
We usually ask whether LLMs give the correct answer. But what if there is no correct answer? In our new
@pnas.org paper, Gustavo Umbelino and I benchmark LLMs against human collective reasoning. #AI, #LLM @zdaarau.bsky.social @ipz.bsky.social , @uzh-ch.bsky.social www.pnas.org/doi/10.1073/...
pnas.org
Plausible nonsense and deliberative reasoning: Benchmarking LLMs against human judgment | PNAS
Large Language Models (LLMs) are entering democratic contexts as instruments of governance,
where the challenges at hand are ill-structured, marked...
