News for hackers. Stuff that matters.
Re:Do Large Language Models learn world models or just surfa... by YeGoblynQueenne on Sunday January 22, 2023 @09:43AM (#34477807)
>> They've been able to demonstrate that the trained Othello player has a model.

They haven't demonstrated that, it remains a conjecture. They show some evidence that they claim supports their conjecture. This evidence comes from "probing" (the classifier-based method you describe) which is a heuristic method that lacks the power to demonstrate anything conclusively. This is as the authors point out:

It’s believed that the higher accuracy these classifiers can get, the better the activations have learned about these real-world properties, i.e., the existence of these concepts in the model.

"It's believed" as in, we don't know, therefore we can't use to demonstrate.

There are no comments on this comment yet.