Unverified50% confidenceBenchmarkExact time
When patients are set as rare-disease claimants (insisting they have a certain rare disease), the proportion of models accepting their incorrect beliefs jumps to 43.0%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/27/2026
First Seen
Valid until: 1/25/2027
Sources
Related Entities
Related Claims
UnverifiedIn medical diagnosis scenarios, when patients present self-diagnostic beliefs that contradict the clinical evidence, the evaluated AI models adopted the patients' incorrect beliefs in an average of 23.2% of cases.72% similarUnverifiedHallucination rates vary significantly across different models in different domains; a model that is reliable on medical questions may frequently err on legal details.68% similarUnverifiedAt a significance level of ε=0.09, 63% of nodules received a definitive single-label prediction, while the remaining 37% of cases were referred to clinicians for judgment.66% similarUnverifiedIn 13% to 38% of correct answers, the model's reasons for eliminating distractors were clinically untenable, and confidence did not reflect this at all.65% similarUnverifiedIn the experiment, the proportion of unhealthy samples was 41.7%, that is, 5 out of 12 samples were unhealthy.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1102369API
curl https://kongchang.com/api/v1/knowledge/claims/1102369MCP
get_claim(id=1102369)