Kanishka Misra 🌊
@kanishka.bsky.social
Assistant Professor of Linguistics, and Harrington Fellow at UT Austin. Works on computational understanding of language, concepts, and generalization.
🕸️👁️: https://kanishka.website
🕸️👁️: https://kanishka.website
omg somehow bluesky doesn't notify me of replies anymore -- my bad! These responses make sense! I guess m and g can be readily swapped in your framework :) Super neat, and nice to see minimal pairs being formalized -- now I can simply point to the paper instead of lengthy explanations!
November 13, 2025 at 2:05 AM
omg somehow bluesky doesn't notify me of replies anymore -- my bad! These responses make sense! I guess m and g can be readily swapped in your framework :) Super neat, and nice to see minimal pairs being formalized -- now I can simply point to the paper instead of lengthy explanations!
Though I also wonder if all of this generalizes to the inverse case of meaning-seeking minimal pair stimuli
bsky.app/profile/kani...
bsky.app/profile/kani...
I am 100% on board with this framing, but wondering if it’ll hold for minimal pair stimuli that are both grammatical but convey very different messages, an example from COMPS:
A robin can fly.
A penguin can fly.
(Similarly for datasets like EWoK)
A robin can fly.
A penguin can fly.
(Similarly for datasets like EWoK)
November 11, 2025 at 1:32 PM
Though I also wonder if all of this generalizes to the inverse case of meaning-seeking minimal pair stimuli
bsky.app/profile/kani...
bsky.app/profile/kani...
I am 100% on board with this framing, but wondering if it’ll hold for minimal pair stimuli that are both grammatical but convey very different messages, an example from COMPS:
A robin can fly.
A penguin can fly.
(Similarly for datasets like EWoK)
A robin can fly.
A penguin can fly.
(Similarly for datasets like EWoK)
November 11, 2025 at 1:15 PM
I am 100% on board with this framing, but wondering if it’ll hold for minimal pair stimuli that are both grammatical but convey very different messages, an example from COMPS:
A robin can fly.
A penguin can fly.
(Similarly for datasets like EWoK)
A robin can fly.
A penguin can fly.
(Similarly for datasets like EWoK)
Chris Potts on Twitter, circa 2023: language models are outstanding (lmao)
November 10, 2025 at 12:18 PM
Chris Potts on Twitter, circa 2023: language models are outstanding (lmao)
Congratulations!!!
November 10, 2025 at 1:09 AM
Congratulations!!!
Keeping it ambiguous as always 🥸😎
November 5, 2025 at 1:32 PM
Keeping it ambiguous as always 🥸😎
Of course!! Thanks so much for the kind words — it’s just a bunch of modifications I made over the old Hugo academic theme!
November 4, 2025 at 2:29 PM
Of course!! Thanks so much for the kind words — it’s just a bunch of modifications I made over the old Hugo academic theme!