Unverified50% confidenceFactExact time
If evaluation samples (including near-duplicate samples) appear in the training data, scores reflect memorization ability rather than genuine skill.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIf evaluation benchmarks are highly aligned with training data, surpassing them reflects overfitting-style specialization rather than genuine capability improvement.79% similarUnverifiedRecursive training makes extensive use of task completion rates and code execution results as reward signals, lacking explicit supervision for narrative consistency, which may lead to catastrophic forgetting of general language modeling capabilities, and this is more pronounced in models with small parameter counts.75% similarUnverifiedIn agent training, behavioral monitoring is just as important as outcome monitoring; looking only at pass rates or scores is insufficient to uncover design flaws in the training environment.74% similarUnverified高频次的形成性反馈是提升技能习得效率的核心变量，而传统临床带教模式因资源限制难以保证73% similarUnverified解决灾难性遗忘的方案是在训练时混入10%-20%的原始预训练数据73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1005177API
curl https://kongchang.com/api/v1/knowledge/claims/1005177MCP
get_claim(id=1005177)