Unverified50% confidenceFactExact time
To achieve continuous growth, the problem of 'catastrophic forgetting' must be solved - training on new data overwrites old knowledge.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe true difficulty of model fine-tuning lies in the construction and cleaning of high-quality training data, preventing catastrophic forgetting, and inference deployment after quantization.73% similarVerifiedCatastrophic forgetting is a classic problem in the field of neural networks; as early as the 1990s, researchers discovered that the performance on old tasks drops sharply when neural networks are continuously trained on new tasks68% similarVerifiedCognitive science research indicates that 'desirable difficulties' during the learning process are crucial for the formation of long-term memory.67% similarUnverifiedMistake-Aware Training和RISE（Recursive Introspection）等研究方法将失败轨迹的利用作为核心机制，在复杂编程和数学推理任务上取得显著性能提升67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1015757API
curl https://kongchang.com/api/v1/knowledge/claims/1015757MCP
get_claim(id=1015757)