Get the latest Science News and Discoveries

AI makes human-like reasoning mistakes - EurekAlert


Large language models (LMs) can complete abstract reasoning tasks, but they are susceptible to many of the same types of mistakes made by humans. According to the authors, LMs trained on human data seem to exhibit some human foibles in terms of reasoning—and, like humans, may require formal training to improve their logical reasoning performance.

None

Get the Android app

Or read this on Eureka Alert

Read more on:

Photo of Human

Human

Photo of EurekAlert

EurekAlert

Related news:

News photo

Alcoholic liver disease in China: A disease influenced by complex social factors that should not be neglected - EurekAlert

News photo

Ultrasonography of hepatocellular carcinoma: From diagnosis to prognosis - EurekAlert

News photo

Capturing carbon with energy-efficient sodium carbonate−nanocarbon hybrid material - EurekAlert