Unverified50% confidenceBenchmarkExact time
Ablation experiments show that allowing the reasoning agent to read the Wiki layer during training leads to a drop in win rate.
1
Sources
50%
Confidence
Long-term
Relevance
8/31/2026
First Seen
Sources
Related Entities
Related Claims
Unverified小模型在分布内高性能的同时存在分布外脆弱性，一旦推理时的工具描述措辞、参数命名或用户查询风格偏离训练集，成功率可能显著下滑70% similarUnverifiedExperiments show that after only a few generations of self-training, the variance of model outputs drops sharply and the text tends toward homogeneity70% similarUnverifiedDuring cross-domain fine-tuning, an excessively large learning rate will destroy pre-trained weights, while an excessively small one will result in almost no learning, requiring a careful trade-off.69% similarVerified量化会不可避免地引入精度损失，在逻辑推理等对准确性敏感的任务上可能出现性能下降67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/830036API
curl https://kongchang.com/api/v1/knowledge/claims/830036MCP
get_claim(id=830036)