Updated
Updated · Computerworld · Aug 20
Study Finds AI Explanations Raise False Negatives in 228-Person Innovation Test
Updated
Updated · Computerworld · Aug 20

Study Finds AI Explanations Raise False Negatives in 228-Person Innovation Test

3 articles · Updated · Computerworld · Aug 20

Summary

  • 228 experienced evaluators reviewing nearly 50 MIT challenge submissions were more likely to make worse calls when an LLM explained its pass-fail recommendation, especially by rejecting ideas human experts would have advanced.
  • 67% of LLM recommendations were accepted overall; reviewers agreed with AI about 75% of the time but matched human-only decisions just 54%, showing how strongly the tools swayed judgment.
  • Narrative rationales were the main problem: they suppressed productive overrides, gave reviewers ready-made reasons to reject proposals, and amplified negativity bias, while black-box recommendations improved alignment with expert baselines.
  • The researchers from Harvard, MIT and the University of Washington said enterprises should treat AI explanations as behavioral interventions, using testing, uncertainty disclosures or even simpler recommendations in high-stakes screening tasks.

Insights

Why might the push for explainable AI secretly be sabotaging our best innovations and leading experts to make worse decisions?
If black-box algorithms outperform AI that explains its reasoning, how can businesses legally justify relying on systems they cannot understand?