GPT-4V Has Directional Dyslexia

Shows our study based on the WSDM 2023 Toloka VQA Challenge

A year has passed since the Toloka Visual Question Answering (VQA) Challenge at the WSDM Cup 2023, and as we predicted back then, the winning machine-learning solution didn’t match up to the human baseline. However, this past year has been packed with breakthroughs in Generative AI. It feels like every other article flips between pointing out what OpenAI’s GPT models can’t do and praising …

challenge generated gpt gpt-4 gpt-4v human llm machine match question question answering shows solution study thoughts-and-theory toloka visual vqa