In last week’s seminar session @anaryegen.bsky.social talked about Mining Argument Structures in Medical Texts (aclanthology.org/2024.emnlp-m...) and Enhancing Factuality in Counter-argument Generation with real-time Knowledge (to be presented at #ACL2025NLP btw, preprint: arxiv.org/pdf/2503.05328)

🧙‍♂️ New paper 🧙‍♀️:
Presenting Wicked: a simple automated method to make MCQA benchmarks more challenging. Wicked shook up 18 open-weight LLMs on 6 benchmarks, with up to 19.7% performance drop with direct prompting 🤯
Paper: shorturl.at/1CGq0
Code: shorturl.at/n2nCU

I couldn't be happier! Preparing the trip to #NeurIPS2024 we received the notification of acceptance of our paper in #COLING2025 with Paula Ontalvilla and Aitor Ormazabal. Paula has just started with her PhD at @hitz-zentroa.bsky.social and she is already publishing at this level!

Meet OLMo 2, the best fully open language model to date, including a family of 7B and 13B models trained up to 5T tokens. OLMo 2 outperforms other fully open models and competes with open-weight models like Llama 3.1 8B — As always, we released our data, code, recipes and more 🎁

Looking at ICLR submissions with the lowest score - What a work of art! 🧵

We launched Judge Arena with @huggingface.bsky.social
@clefourrier.bsky.social - a platform that lets you easily compare models as judges side-by-side and vote for the best evaluation

Check out the live leaderboard and start voting now 🤗