Unverified50% confidenceOpinionExact time
The median improvement of 5.3 percentage points indicates that current models are mostly doing 'local patching' and have not yet formed cross-level knowledge accumulation, which is the key difference between continual learning and single-round self-correction.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/27/2026
First Seen
Valid until: 1/25/2027
Sources
Related Entities
Related Claims
UnverifiedUnder a local quadratic model, a larger batch means fewer but longer update steps, with each step incurring a greater loss on curvature, resulting in a critical batch size that depends on the learning rate, beyond which sample efficiency declines.76% similarUnverifiedDuring joint fine-tuning, a lower learning rate helps stabilize policy updates and avoid destroying fine-grained behaviors that have already been learned.72% similarUnverified数据规模的增长并不等同于有效学习信号的增长，在模型能力提升到一定阈值后简单堆砌样本的收益会急剧下降71% similarUnverifiedAny study comparing fine-tuning schemes with different numbers of trainable parameters should be wary of the shared learning rate trap; otherwise, conclusions that fewer parameters yield better results may need to be revisited.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1102571API
curl https://kongchang.com/api/v1/knowledge/claims/1102571MCP
get_claim(id=1102571)