Unverified50% confidenceFactExact time
The author claims that the off-the-shelf model they started with, faced with 85 hidden allergen samples, never output "uncertain".
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/18/2026
First Seen
Valid until: 1/16/2027
Sources
Related Entities
Related Claims
UnverifiedThe fine-tuned model learned to refuse (saying "not sure"), whereas the base model never said "not sure" in 85 opportunities.70% similarUnverifiedThe author tested 5 local models ranging from 1B to 8B parameters on their own machine at temperature zero, and every single one produced a 100% false-confidence rate on at least one entire format.68% similarUnverifiedRanked by question difficulty, persistence rate was 91.4% on the 60 questions that all models answered correctly, but only 73.5% on the 52 questions that at least one model got wrong, indicating that sycophancy tracks uncertainty.65% similarVerifiedIn scenarios with extreme class imbalance, even an accuracy as high as 95% may indicate that the model is completely unable to identify the minority class.63% similarUnverifiedThe experiment has a small sample size (single model, single test, 50 questions), is subject to random fluctuation, and constitutes a heuristic finding rather than a definitive conclusion.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1060638API
curl https://kongchang.com/api/v1/knowledge/claims/1060638MCP
get_claim(id=1060638)