Unverified50% confidenceTradeoffExact time
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
1
Sources
50%
Confidence
Long-term
Relevance
7/15/2026
First Seen
Sources
Related Claims
Unverified端到端模型的核心优势在于避免模块间信息损失和误差累积，但代价是可解释性低、对训练数据分布敏感、难以应对长程推理任务81% similarUnverified仅用成功轨迹训练的模型往往存在分布外泛化的严重缺陷，遇到工具返回错误时便丧失纠偏能力80% similarUnverifiedBehavioral cloning simplifies the problem to supervised learning, but suffers from distribution shift, where differences between the state distributions at training time and execution time lead to error accumulation.76% similarUnverifiedThe understanding of text-to-image models is essentially large-scale statistical association, and generation quality drops significantly when dealing with long-tail concepts that appear rarely in the training set.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/518118API
curl https://kongchang.com/api/v1/knowledge/claims/518118MCP
get_claim(id=518118)