Unverified50% confidenceSolutionExact time
用新数据更新模型时可能破坏原有能力，即灾难性遗忘，工业界通过失败案例库、数据增强与混合回放技术来整合新数据
1
Sources
50%
Confidence
Long-term
Relevance
7/15/2026
First Seen
Sources
Related Claims
UnverifiedIf only the data of newly added classes is used to fine-tune an expanded classification head, the model is highly prone to catastrophic forgetting, rapidly losing its ability to recognize the original classes.74% similarUnverifiedFine-tuning burns knowledge into model weights, making knowledge updates costly as they require retraining; RAG stores knowledge in an external database, so updates only require modifying the database without changing the model.71% similarUnverified数据泄漏是因意外引入测试集信息而导致模型评估虚高的陷阱，常见形式包括在划分数据集之前就对全量数据做标准化或使用时间上因果倒置的特征70% similarUnverified工具调用使攻击面从让模型说错话升级为让模型做错事，危害从信息误导上升为实质性的数据访问和系统篡改70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/511170API
curl https://kongchang.com/api/v1/knowledge/claims/511170MCP
get_claim(id=511170)