amazingly, our conspiracy dataset paper 'Mute Cods' was accepted to #LREC2026! big thanks & huge shoutout to the (many) people involved 🫶 this truly was a collaborative effort and I'm glad & proud that we got so many of the Hybrids people together, happily united on three author lines 🤘 #MSCA

🚨 NEW PAPER ALERT 🚨 Dialz: A Python Toolkit for Steering Vectors ArXiv: arxiv.org/abs/2505.06262 Docs: cardiffnlp.github.io/dialz/ Repo: github.com/cardiffnlp/d... A Python package to help you create, apply and visualise steering vectors for anything you want - from sycophancy to bias.

Expert + LLM = Better Sexism Detection? ✨ Paper: 𝘛𝘦𝘭𝘭 𝘔𝘦 𝘞𝘩𝘢𝘵 𝘠𝘰𝘶 𝘒𝘯𝘰𝘸 𝘈𝘣𝘰𝘶𝘵 𝘚𝘦𝘹𝘪𝘴𝘮: 𝘌𝘹𝘱𝘦𝘳𝘵-𝘓𝘓𝘔 𝘐𝘯𝘵𝘦𝘳𝘢𝘤𝘵𝘪𝘰𝘯 𝘚𝘵𝘳𝘢𝘵𝘦𝘨𝘪𝘦𝘴 𝘢𝘯𝘥 𝘊𝘰-𝘊𝘳𝘦𝘢𝘵𝘦𝘥 𝘋𝘦𝘧𝘪𝘯𝘪𝘵𝘪𝘰𝘯𝘴 𝘧𝘰𝘳 𝘡𝘦𝘳𝘰-𝘚𝘩𝘰𝘵 𝘚𝘦𝘹𝘪𝘴𝘮 𝘋𝘦𝘵𝘦𝘤𝘵𝘪𝘰𝘯 w: @indiiigo.bsky.social, @matteo-mls.bsky.social y.social & @gabriellalapesa.bsky.social @ Findings #NAACL2025 !🤩