Folks, some Conference on Language Modeling stats, because looking at these really brightens the mood :)
We received a total of ⭐️1036⭐️ submissions (for the first ever COLM!!!!). What is even more exciting is the nice distribution of topics and keywords. Exciting times ahead! ❤️

I've just finished Appendix F and sent in my paper. Good luck to all 😎
(What do you mean I have too many appendices?)

Following multiple queries about ARR, it is important to clarify that COLM doesn't allow for double submissions

colmweb.org/faq.html

🚨🚨🚨 New paper on LMs trained with machine translated data!

We all know that billions to trillions of tokens are needed to get the best LLMs. But not all languages have such data.

Q: What to do?
A: Just create it using machine translation!

Paper: arxiv.org/abs/2403.13638

🎬Témoignage de Fanny Jourdan, doctorante en informatique en #IntelligenceArtificielle à ANITI Toulouse IRIToulouse, qui présente son métier.
🙌Encourageons les talents féminins vers les métiers du numérique ! #JournéeDesDroitsDesFemmes
👉 …-numerique-educatif.apps.education.fr/w/hhMxpX82D4PX…

Fiers que Fanny Jourdan, doctorante IRIT - ANITI Toulouse soit finaliste de cette édition régionale 2024.

Excited to present my recent work on Inseq and the #ICLR2024 PECoRe interpretability framework for the Sheffield NLP group this afternoon! Many thanks casszhao for inviting me! 🤗

🐛 Inseq: github.com/inseq-team/ins…
🐑🐑 PECoRe: openreview.net/forum?id=XTHfN…

👋👨‍🍳🍵 After a year of cooking up a secret project, I'm thrilled to officially reveal:

The 𝐋𝐄𝐍𝐒 𝐏𝐫𝐨𝐣𝐞𝐜𝐭.

By combining modern tools of Explainable AI, how much can we explain a ResNet50?

🧶

Introducing WebLINX 🐯, a large benchmark for AI agents navigating real websites with multi-turn dialogue. 100K interactions across 2300 demonstrations on 150 real-word websites. Includes HTML, screenshots and videos. Tests unseen sites, tasks, blind users
arxiv.org/abs/2402.05930

👋 Check out our new paper and benchmark: REVEAL, a dataset with step-by-step correctness labels for chain-of-thought reasoning in open-domain QA

🧵🧵🧵

arxiv.org/abs/2402.00559

huggingface.co/datasets/googl…

We're organizing a new workshop on data contamination (CONDA) at ACL2024! CFP below

Contamination is when test data was included in training, for any reason. A lot of research is needed to understand when this happens, or prevent it. Consider submitting!

twitter.com/osainz59/statu…

Hi! Could you send me the most interesting/underrated articles you've read about RAGs?
I'd like to learn more about this topic 🧐

Interpretability research is popular these days, but public attention is still mostly focused on improving task performance.

To reverse this trend, I started curating a Hugging Face collection of daily picks in interpretability & analysis of LMs! 🔍 huggingface.co/collections/gs…