Are Emergent Abilities in Large Language Models just In-Context Learning? This is the topic of
@IGurevych
's talk at the Symposium on Large Language & Foundation Models of
@ELLISforEurope
,
@ai4mediaproject
&
@AIDAdocAcademy
on October 17/18, Amsterdam:
➡️
Are Emergent Abilities in Large Language Models just In-Context Learning?
Spoiler: YES 🤯
Through a series of over 1,000 experiments, we provide compelling evidence:
Our results allay safety concerns regarding latent hazardous abilities.
A🧵👇
#NLProc
@IBigoulaeva
@rachneet4
@harish
@IGurevych
@BathNLP
The registration for the symposium is now closed since the maximum capacity has been reached. If you haven't registered, you can still watch the livestream on YouTube on October 17/18, 2023, at