interesting, but I don't agree that if we see the "token reasoning" chain it somehow explains how the model got the final answer. what if we trained deceiver models that would provide a sound chain of explanation but…
I mean, SSMs are in fact under the hood RNNs
interesting, but I don't agree that if we see the "token reasoning" chain it somehow explains how the model got the final answer. what if we trained deceiver models that would provide a sound chain of explanation but…
I mean, SSMs are in fact under the hood RNNs