cross-posted from: https://programming.dev/post/36289727
Comments
Our findings reveal a robustness gap for LLMs in medical reasoning, demonstrating that evaluating these systems requires looking beyond standard accuracy metrics to assess their true reasoning capabilities.6 When forced to reason beyond familiar answer patterns, all models demonstrate declines in accuracy, challenging claims of artificial intelligence’s readiness for autonomous clinical deployment.
A system dropping from 80% to 42% accuracy when confronted with a pattern disruption would be unreliable in clinical settings, where novel presentations are common. The results suggest that these systems are more brittle than their benchmark scores suggest.
flipping a coin fails spectacularly at making any decisions other than what to have for dinner
You’ve summarized the value of current generation AI well.
It excels exactly when the result doesn’t matter in the slightest.