Unverified50% confidenceFactExact time
Fine-tuning carries the risk of catastrophic forgetting, where fine-tuning for a specific behavior may degrade the model's performance on other tasks.
1
Sources
50%
Confidence
Long-term
Relevance
10/7/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAn intermittently faulty memory module may alternately produce correct and incorrect computation results, causing sporadic deviations in gradient calculations during neural network training, affecting model convergence without triggering hardware alerts.77% similarUnverified针对某类任务的专项强化往往以牺牲其他任务的表现为代价，此现象被称为灾难性遗忘77% similarUnverified差分隐私训练、去重预处理和机器遗忘等缓解记忆化的技术方案均会在不同程度上牺牲模型性能76% similarUnverified当模型同时优化任务准确性和置信度校准时，两个梯度方向可能相互干扰，涉及灾难性遗忘和目标冲突问题75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/985039API
curl https://kongchang.com/api/v1/knowledge/claims/985039MCP
get_claim(id=985039)