Unverified50% confidenceBenchmarkExact time
Overall accuracy remained almost unchanged: agreement with humans was 54.4% without images, 53.7% with aligned images, and 54.7% with misleading images.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe mean accuracy difference of occupational profiles relative to the minimal baseline was -0.6 percentage points, with a 95% bootstrap interval of [-1.5, +0.2].79% similarUnverifiedIn scenarios where AI-generated works account for a low proportion (e.g., only 5%), even with a detection accuracy of 90%, more than two-thirds of the flagged works are actually human-created—this is the base rate fallacy in Bayesian reasoning.71% similarUnverified推荐为每个人注册5-10张不同条件下的照片，使用多模板平均向量可将识别准确率提升2-5个百分点69% similarUnverified研究表明人类评估者在判断LLM输出的事实准确性时，正确率往往只有50%-70%69% similarUnverifiedAmong all 13 models, only 37% of samples with label changes shifted toward the misleading image's meaning, while 63% went in the opposite direction, both below the 50% random baseline, indicating that images merely randomly disrupted model judgments rather than guiding them.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/977923API
curl https://kongchang.com/api/v1/knowledge/claims/977923MCP
get_claim(id=977923)