Booth 21-25 | AI Data Management Zone | Tokyo Big Sight
For most of the last six years, the most capable LLMs were locked behind APIs. You could call them, you could build on them, but you couldn’t look inside, customize
A new paper from Christopher Burger, Karmece Talley, and Christina Trotter (arXiv:2512.23587), accepted to the 59th Hawaii International Conference on System Sciences, asks a deceptively simple question: can today’s frontier LLMs reliably identify AI-generated text? They tested GPT-4, Claude, and Gemini in a computing-education setting, where the stakes — academic
