How do multilingual LLMs process bilingual words?
Do they approach it like humans?
Our paper explores LLM's processing of cognates, non-cognates, and interlingual homographs, uncovering LLMs' strengths & limits in bilingual processing! w/
Tanmoy Chakraborty
and Gayatri Oke.
1/π§΅
An screenshot of UnicodeIt website
Write math on π¦ with UnicodeIt!
For example: ΞΈ β ββΏ or ppΜ
β ΞΌβΊΞΌβ»
Use website or install system-wide in Linux, macOS, or windows
www.unicodeit.net
(Created several years ago with @svenkreiss.bsky.social)
π’ NAACL reviews have been released!
π feature alert: ARR now has review issue flagging! Thanks @jkkummerfeld.bsky.social & OR team for help with implementation, and other EiCs for supporting the idea! It'll be live after author response. More details here: aclrollingreview.org/authors#step...
/1
How do LLMs learn to reason from data? Are they ~retrieving the answers from parametric knowledgeπ¦? In our new preprint, we look at the pretraining data and find evidence against this:
Procedural knowledge in pretraining drives LLM reasoning βοΈπ’
π§΅β¬οΈ
Ok, I am so excited about this!
I built a new algorithmic ranked feed based off my starter pack, and did it on skyfeed.app
I'm probably going to tweak mine a bit, if you wanted a ranked feed of the best post from a selected list of followers, here is how you can do it. 1/8π§΅
π§ͺ π©Ίπ₯οΈ π #AcademicSky
πββοΈ
Nice initiative! π―
Can you add as well!? Would love to interact with the CSS community!
Great initiative! π―
Can you add me as well?
Great initiative! π―
@mginn.bsky.social Can you please add me too?!
