A break from the usual #ACL2024 program: Preethi Seshadri 🔥is working with me on open research for fairness of LLMs in hiring. 👇 is a short form to share a resume so we can check our synth data is predictive of real data. Please help! 🙏💖 (no training/ sharing, we delete it after)

Time for the first Keynote from Isabelle Augenstein at genderbiasnlp! #ACL2024

A good reminder for those of us in LLM land (like me) that we don't only need to mitigate gender biases *caused* by LM generation, but we should enable researchers to *use* LMs to discover biases in human content. From Isabelle Augenstein's keynote genderbiasnlp #ACL2024

The Oral paper presentation are starting now genderbiasnlp #ACL2024 !

First oral in genderbiasnlp on stereotype reduction -- it's nice to see human evals on stereotypes instead of just benchmark results! *especially* because the benchmarks are so flawed (srsly don't use just the benchmarks) #ACL2024

Third oral on gender bias detection in training data itself. genderbiasnlp #ACL2024

Fourth oral at genderbiasnlp on gender bias in relation extraction #ACL2024

Final oral of genderbiasnlp ! Actually being given by my MSc supervisor Fei 😂🔥 who is the last author. They do a super detailed taxonomy of gender bias types (way beyond usual) and use it to analyse bias in educational materials.

Our second and final keynote with Hal Daumé III is now! genderbiasnlp #ACL2024

Last event of the day genderbiasnlp , the lightning talks!! Particularly love this one so far: an analysis of over refusal of certain identities in LLMs 🔥. We also don't talk about how safety tuning risks exacerbating erasure of minorities 🙊. We should 📢. #ACL2024

A cool survey from our genderbiasnlp lightning talks: it's a nice visualisation of longitudinal fads in measurement and debiasing in language models #ACL2024