LLM performances have been plateauing... so we decided to make the Open LLM Leaderboard steep again 🏔️ 😈

Introducing the Leaderboard 2️⃣

Expect...
- new benchmarks
- fairer reporting
- cool features (did I hear voting and chat template?)

🧵

huggingface.co/spaces/open-ll… Over the last year, our benchmarks slowly became overused and saturated:
- models got way better at them and we reached saturation
- people starting to over optimize for the leaderboard
- and we also observed some contamination...

So it was time for a change!

For the last months @huggingface, I worked on transformers and... graphs!

So here is a small blog, if you wonder what one could use graphs for, or how to machine learn on them 🔎
(Spoiler: they are everywhere 🧬🚗✍️)

huggingface.co/blog/intro-gra… In this post, you'll discover:
- what graphs are, why they are used, how to represent them
- how people learn on graphs, from pre-neural methods to Graph Neural Networks
- the very recent world of Transformers for graphs

#acl2022nlp
What happens inside a multilingual neural cognate prediction model?
We show that predicting cognates between current Romance languages latently teaches the model about their proto-forms, allowing reconstruction without fine-tuning encoders on the task!🧵 In layman's terms, learning to predict special words (cognates) between related languages (French, Italian, Spanish, Portuguese, Galician, Catalan, Occitan, Romanian, and Aromanian) gives the model 'intuitive' knowledge about their parent, Latin!