I'll speak about building community-centred harm taxonomies at the “Measuring and mitigating bias in AI” workshop, April 29th, 11am-3pm, Amsterdam. amsterdamnlp.github.io/blog/biaswor... in connection with the PhD defence of @ovdw.bsky.social #NLProc #bias #AI

📢 We are seeking #PhD students for a fully funded research project (open to local & international applicants) @sheffieldnlp.bsky.social . This project is supported by a cross-discipline supervision team and opportunities. www.findaphd.com/phds/project...

How do LLMs learn to reason from data? Are they ~retrieving the answers from parametric knowledge🦜? In our new preprint, we look at the pretraining data and find evidence against this: Procedural knowledge in pretraining drives LLM reasoning ⚙️🔢 🧵⬇️