🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

What would it take for AI evaluations to truly support our global experiences? 🌍 Our cross-institutional paper introduces INCLUDE, a multilingual LLM evaluation benchmark of local exams capturing in-language nuances & cultural context for truly localized AI evaluation.

🟢LingOly: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low-Resource and Extinct Languages Oral Session 4A, Thursday 15:30-16:30 TLDR: We construct a hard reasoning eval that controls for memorisation using low-resource languages. Work led by Andrew Bean

I really enjoyed working on this paper with such an amazing team — in the true spirit of Ubuntu, making sure AI models are accessible and work equally well for everyone. Happy to see it accepted at #FAccT2025! 🎉

A little late to the party, but 2/2 papers got accepted to #ACL2025🎉 work from the first year of my PhD and collaboration from my internship at J.P. Morgan. Will share more deets on the papers soon, but can’t wait to run the Kipchoge 🇰🇪🐐 loop in Vienna.

Check out Deep Learning Indaba feature on Nature ✨💪🏾❤️ nature.com/articles/d4414…

Our work, AfriMed-QA has been accepted to #ACL2025 main track! In it, we introduce a Pan-African, multi-specialty medical QA benchmark to rigorously evaluate how LLMs perform across several medical specialties focused on Africa. 1\n

🚨 Are we misusing the term Multi-Agent Systems in LLM research? 🚨 Find out more in our latest preprint: "Large Language Models Miss the Multi-agent Mark" More info ⬇

Wrote on how our protests continue to be limited and co-opted by the saturation of infrastructure-led politics.. Pambazuka News Issue 899 pambazuka.org/Infrastructure…

🏆 We are honoured to receive a Best Paper Awards Honourable Mention at #FAccT2025 for “The World Wide Recipe”, a community-centric framework tackling representational gaps. A true work of Ubuntu 🌍 📄 Paper -> arxiv.org/abs/2406.09496

Using #LLMs to improve claim matching and #misinformation response. Come see our poster at #ACL2025NLP now (#430) or read the paper. aclanthology.org/2025.findings-…