This exciting study reveals that just like us, AI has its own biases that can skew its thinking, especially when solving problems. Understanding and...
This study explores how the order of retrieved evidence can impact the performance of AI systems, revealing a 'U-shaped' effect on accuracy. Understanding this...
This research explores if AI-created test collections for evaluating search engines can be trusted, especially considering potential biases. Understanding this could change how we...
This research looks at whether everyday tools like ChatGPT follow ethical and social norms in our lives. It highlights key challenges and obstacles in...
Our research uncovers how AI models may be tricked by misleading visual cues, impacting their reliability in tasks like object recognition. Understanding and fixing...
Artificial intelligence could speed up the peer review process in economics but watch out—it might favor certain groups over others and struggle with AI-generated...