Unverified50% confidenceTradeoffExact time
Raising the share of risky-conversation samples from 10% to 25% improves standalone safety-check recall (53% to 68%) but causes the model to raise more false alarms on ordinary chat; using risky samples only for training the safety question can mitigate the side effects.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedResearch shows that after conducting 3–5 high-quality mock interviews, candidates' actual interview pass rates can improve by 20–30%, primarily due to reduced on-the-spot anxiety and the establishment of structured problem-solving and communication habits.69% similarUnverified在小样本LoRA训练中，rank值设置存在偏差-方差权衡，实践中rank=4至32是常见的安全区间68% similarUnverifiedResearch indicates that an attacker needs to modify as little as 0.01% of training data to potentially implant backdoor behaviors in a model that are undetectable by standard evaluations.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1062486API
curl https://kongchang.com/api/v1/knowledge/claims/1062486MCP
get_claim(id=1062486)