iiinova — where your digital self keeps evolving

Aryaman Arora

@aryaman.io

2.8K followers 486 following 24 posts

member of technical staff @stanfordnlp.bsky.social

Posts Replies Media

Reposted by Aryaman Arora

juliekallini.bsky.social @juliekallini.bsky.social · 14/01/2025

"Mission: Impossible" was featured in Quanta Magazine! Big thank you to @benbenbrubaker.bsky.social for the wonderful article covering our work on impossible languages. Ben was so thoughtful and thorough in all our conversations, and it really shows in his writing!

0133

Reposted by Aryaman Arora

Chris Potts @cgpotts.bsky.social · 13/01/2025

I've posted the practice run of my LSA keynote. My core claim is that LLMs can be useful tools for doing close linguistic analysis. I illustrate with a detailed case study, drawing on corpus evidence, targeted syntactic evaluations, and causal intervention-based analyses: youtu.be/DBorepHuKDM

youtu.be

Finding linguistic structure in large language models

YouTube video by Chris Potts

17420

Aryaman Arora @aryaman.io · 25/11/2024

hmm bluesky feed is 80% reviewing complaints. twitter is slightly better in this regard

2260

Aryaman Arora @aryaman.io · 25/11/2024

it's pretty interesting how (some?) Sino-Tibetan languages, when they historically underwent too much degradation through sound change, just decided to make compounds with synonymous elements or stick semantic prefixes on everything

1100

Aryaman Arora @aryaman.io · 22/11/2024

made this thing, reply to be added go.bsky.app/AKGJ82V

6121

Aryaman Arora @aryaman.io · 20/11/2024

caleb is so cool pls follow

150

Reposted by Aryaman Arora

Juan Diego Rodriguez @juand-r.bsky.social · 08/11/2024

How do language models organize concepts and their properties? Do they use taxonomies to infer new properties, or infer based on concept similarities? Apparently, both! 🌟 New paper with my fantastic collaborators @amuuueller.bsky.social and @kanishka.bsky.social

Title: "Characterizing the Role of Similarity in the Property Inferences of Language Models"
Authors: Juan Diego Rodriguez, Aaron Mueller, Kanishka Misra

Left figure: "Given that dogs are daxable, is it true that corgis are daxable?" A language model could answer this either using taxonomic relations, illustrated by a taxonomy dog-corgi, dog-mutt, canine-wolf, etc., or by similarity relations (dogs are more similar to corgis than cats, wolves or shar peis).

Right figure: illustration of the causal model (and an example intervention) for distributed alignment search (DAS), which we used to find a subspace in the network responsible for property inheritance behavior. The bottom nodes are "property", "premise concept (A)" and "conclusion concept (B)" , the middle nodes are "A has property P", "B is a kind of A", and the top node is "B has property P".

410822

Aryaman Arora @aryaman.io · 14/11/2024

wow i have so many followers here somehow, is it time to start posting here too

3140

Reposted by Aryaman Arora

Naomi Saphra @nsaphra.bsky.social · 05/01/2024

I decided what we need to make blueskAI happen is a feed. Reply here to get added to the whitelist! Whitelisted users can post to the feed by adding the following keywords to a post: 🤖 bskAI blueskAI

624317

Aryaman Arora @aryaman.io · 05/01/2024

Hey @noviscl.bsky.social should we start shitposting here too

000

Aryaman Arora @aryaman.io · 26/07/2023

So Threads got all the AI influencer accounts. This seems to be getting more of the linguists. But I don't think anything will be like Twitter tbh

170

Aryaman Arora @aryaman.io · 01/07/2023

Do I really need to read more than 600 posts a day? The answer is apparently yes

040