Confidence is persuasive. In artificial intelligence systems, it is often misleading. Today’s most capable reasoning models share a trait with the loudest voice in the room: They deliver every answer with the same unshakable certainty, whether they’re right or guessing. Researchers at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) have now traced that overconfidence to a specific flaw in how these models are trained, and developed a method that fixes it without giving up any accuracy. The team’s research is published on the arXiv preprint server.Confidence is persuasive. In artificial intelligence systems, it is often misleading. Today’s most capable reasoning models share a trait with the loudest voice in the room: They deliver every answer with the same unshakable certainty, whether they’re right or guessing. Researchers at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) have now traced that overconfidence to a specific flaw in how these models are trained, and developed a method that fixes it without giving up any accuracy. The team’s research is published on the arXiv preprint server.[#item_full_content]