Thanks a lot! We had an email exchange with the authors and they shared some updated results with much better random shuffling controls on the WordNet hierarchy.
They also argue that some contexts should promote the likelihood of both “sad” and “joy” since they are causally separable, so they should not be expected to be anti-correlated under their causal inner product per se. We’re still concerned about what this means for semantic steering.
Thanks a lot! We had an email exchange with the authors and they shared some updated results with much better random shuffling controls on the WordNet hierarchy.
They also argue that some contexts should promote the likelihood of both “sad” and “joy” since they are causally separable, so they should not be expected to be anti-correlated under their causal inner product per se. We’re still concerned about what this means for semantic steering.