Social Choice Theory: alignment as a Maximal Lottery - Roberto-Rafael Maura-Riverso
Автор: ILIAD Conference
Загружено: 2025-10-23
Просмотров: 117
Описание:
When people disagree about what's right, what should AI do? This is pluralistic AI alignment's core challenge. Voting systems seem natural, but Arrow's impossibility theorem crushed that hope: no perfect voting method exists. Until recently. Stochastic voting systems (maximal lotteries) sidestep these limitations. The question now: how do we make LLMs behave like this ideal system?
Recorded at the ILIAD 2: ODYSSEY Conference in August 2025.
Повторяем попытку...
Доступные форматы для скачивания:
Скачать видео
-
Информация по загрузке: