BIS Bulletins No 83: Testing the cognitive limits of large language models
Our findings do not detract from the considerable progress in central bank applications of machine learning to data management, macro analysis and regulation/supervision. They do, however, suggest that caution should be exercised in deploying LLMs in contexts that demand rigorous reasoning in economic analysis.
Topics
Continue reading with a PwC Plus-Subscription
- verified Information source
- daily updates
- completely searchable articles (with refiner)
- tailored alert
To the top
