Sireesh Gururaja

siree.sh

28 July 2025 22:01

Coming soon (6pm!) to the #ACL poster session: how do experts work with collections of documents, and do LLMs do those things? tl;dr: only sometimes! While we have good tools for things like information extraction, the way that experts read documents goes deeper - come to our poster to learn more!

Gokul Swamy

gokul.dev

21 June 2025 14:30

It was a dream come true to teach the course I wish existed at the start of my PhD. We built up the algorithmic foundations of modern-day RL, imitation learning, and RLHF, going deeper than the usual "grab bag of tricks". All 25 lectures + 150 pages of notes are now public!

Lindia Tjuatja

lindiatjuatja.bsky.social

09 June 2025 14:43

When it comes to text prediction, where does one LM outperform another? If you've ever worked on LM evals, you know this question is a lot more complex than it seems. In our new #acl2025 paper, we developed a method to find fine-grained differences between LMs: 🧵1/9

eleutherai.bsky.social

07 June 2025 22:31

Can you train a performant language model using only openly licensed text? We are thrilled to announce the Common Pile v0.1, an 8TB dataset of openly licensed and public domain text. We train 7B models for 1T and 2T tokens and match the performance similar models like LLaMA 1 & 2

Yong Zheng-Xin (Yong)

yongzx.bsky.social

10 May 2025 16:17

📣 New paper! We observe that reasoning language models finetuned only on English data are capable of zero-shot cross-lingual reasoning through a "quote-and-think" pattern. However, this does not mean they reason the same way across all languages or in new domains. [1/N]