In the Media: Amulya Yadav on AI bias

Amulya Yadav, associate professor in the College of IST, was recently featured in multiple news outlets. He discussed research showcased during the Bias-a Thon competition at Penn State's Center for Socially Responsible AI, for which Yadav serves as associate director of programs.

Bias-a-Thon challenged participants to come up with prompts that would lead generative AI systems to respond with biased answers. The competition demonstrated that intuitive strategies employed by everyday users were just as effective at inducing biased responses as expert technical strategies.

Yadav and his fellow researchers presented their findings at the Eighth AAAI/ACM Conference on AI, Ethics and Society (AIES-25) last month.

• Read "Exposing AI Bias by Crowdsourcing: Democratizing Critique of Large Language Models"
  
• Read "Personal Insights Prove as Potent as Technical Strategies for Unlocking AI Chatbots" at Bioengineer.org
  
• Read In "Lay Intuition Rivals Tech in AI Chatbot Jailbreaking" at Mirage News