Unverified50% confidenceBenchmarkExact time
Perturbation-augmented training can only narrow the probe performance gap to -3.7 percentage points, with limited effectiveness.
1
Sources
50%
Confidence
Long-term
Relevance
9/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMulti-position aggregation is highly effective against local perturbations (loss ≤ 0.5 percentage points), but can only attenuate distributed perturbations, with performance still dropping by approximately 3.8 percentage points.70% similarVerifiedThe marginal returns of simply increasing model parameters and training data are diminishing, a phenomenon known as 'Scaling Law slowdown.'70% similarUnverifiedThe retraining involved a clear trade-off: slight decreases in some very high scores on cleaner validation distributions, in exchange for improved real-world performance.66% similarUnverifiedAll three approaches—pruning, quantization, and distillation—commonly face the problem of significant accuracy degradation after compression, requiring large-scale retraining to recover performance.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/924818API
curl https://kongchang.com/api/v1/knowledge/claims/924818MCP
get_claim(id=924818)