MIT News AI
Teaching AI models to say “I’m not sure”
MIT News AI published: A new training method improves the reliability of AI confidence estimates without sacrificing performance, addressing a root cause of hallucination in reasoning models.
Read originalWhy it matters
This reported AI news may affect AI product capabilities, developer choices, or adoption timing. Review the original source for exact claims and availability.
This page is an independent summary. Facts and availability should be verified in the original publication.
ResearchArtificial intelligenceAlgorithmsMachine learning