Unverified50% confidenceFactExact time
CAGD decouples three roles that are conflated in data replay: the condition (selecting which behaviors to protect), teacher generation (locating where to protect), and soft targets (specifying how predictions may change).
1
Sources
50%
Confidence
Long-term
Relevance
10/7/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedConditional Anchored Generation Distillation (CAGD) is an approach targeting catastrophic forgetting in continual learning of language models; it uses the old model's predictive distribution as the distillation target, protecting model capabilities at the behavioral level rather than the data level.70% similarUnverifiedThe CAAI system design supports comparing multiple configurations under the same scenario, including history influence enabled vs. disabled, the same state with different historical paths, and deterministic vs. probabilistic selection.60% similarUnverifiedMethods for addressing underfitting include adding features, switching to a stronger model, and performing feature engineering; methods for addressing overfitting include adding regularization, reducing features, increasing data, or using cross-validation.58% similarUnverified模板对齐能力在技术上依托RAG或Few-shot Learning机制实现，将企业模板作为上下文示例注入模型推理过程58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/982972API
curl https://kongchang.com/api/v1/knowledge/claims/982972MCP
get_claim(id=982972)