🔥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

Talked about human biases in language models and how they vary across languages with Chahat Raj Antonis Anastasopoulos at EMNLP 2023!

Presented our work ECIR2024 in Glasgow! #SALSA 💃 Leveraging salience scores for crafting interpretable adversarial attacks in fake news detection models. Exciting discussions on enhancing AI robustness, (also ethics, fairness and biases)! Paper: dx.doi.org/10.1007/978-3-…

We have seen the usual man:doctor🧑‍⚕️ and woman:nurse👩‍⚕️ stereotypes. But guess what? VLMs are also throwing out wild associations like blonde:dumb🤦‍♀️, old person:dinosaur🦕, or college student:broke. 🧑‍🎓💸 BiasDora, our #EMNLP2024 Findings Paper: arxiv.org/pdf/2407.02066, explores

I'll be at AI, Ethics, and Society Conference (AIES) with Aylin Kamelia Caliskan and Anjishnu to show how LLM responses imitate human psychology and how we use it to mitigate social bias using the Contact Hypothesis. Listen to our talk on Wednesday, Oct 23rd, when we present bit.ly/BreakingBiasBu… Antonis Anastasopoulos William Zhu

I'll be at #EMNLP2024 with Anjishnu presenting BiasDora. Catch us on Thursday, Nov 14, Session 11. Aylin Kamelia Caliskan Antonis Anastasopoulos William Zhu EMNLP 2025

Stop by Jasmine #20 right now to see how Anjishnu and Chahat Raj explore multimodal LLMs to uncover the implicit associations they make in their BiasDora work

Presenting this at #WACV2025 today + oral session tomorrow. Come say hi if you are around!