The Research Seminar Series in Philosophy invites you to a seminar with Iwan Williams, Copenhagen, "Content determination for AI representations – the disputed roles of structure, selection, and success".
Abstract
What determines the content of internal representations in LLMs, and other AI models? In the first part of the talk, I'll argue that structural correspondences between internal activations in LLMs and real world entities can play a role in grounding representation of those entities. To ground content, however, these correspondences need to be exploited—to play a causal role in explaining the behavioural success of the system. But what fixes the success conditions of an AI model's behaviour? An attractive view appeals to history: successful outcomes are those have have been selected for or stabilised through training. In the second half of the talk, I'll question this final assumption. When explaining an AI system's behaviour, we typically want to understand why it succeeds or fails on our terms, relative to its deployment context, and thus (I'll tentatively suggest) success and failure in this sense are the appropriate explananda for representational explanations in AI.
