Unverified50% confidenceFactExact time
The confidence thresholds recommended by model manufacturers increased the proportion of stereotypes among retained answers on ambiguous BBQ gender questions, with granite-switch's stereotype proportion rising from 0.76 to 0.85 and pplx's from 0.81 to 1.00.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/30/2026
First Seen
Valid until: 1/28/2027
Sources
Related Entities
Related Claims
UnverifiedRaising the confidence level from 95% to 99% (z-value 2.576) will expand the margin of error by approximately 31% for the same sample size.66% similarUnverifiedAblation analysis shows that fine-tuning on the segment paradigm yields a +5.29-point improvement on the test set, while replacing the first 4,500 transcript words with 2,000 retrieved words yields only a +1.55-point improvement.66% similarUnverifiedFormat effect: with the same content changed to Markdown format, 4 of 5 evaluators preferred Markdown over plain text at rates of 73% to 97%, while two human annotators had only a 57% preference rate on 30 sample pairs.65% similarUnverifiedMerely changing the order of options could shift the share of a certain option for GPT-6-luna from 16% to 40%; changing the internal ids of options affected Jev's answers by 37.9 points (out of 100), almost equal to the effect of removing all hand information (37.1 points).65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1115472API
curl https://kongchang.com/api/v1/knowledge/claims/1115472MCP
get_claim(id=1115472)