Unverified50% confidenceCautionExact time
When endowing existing VLMs with generative capabilities, the understanding abilities accumulated during model pretraining are often impaired, resulting in catastrophic forgetting.
1
Sources
50%
Confidence
Long-term
Relevance
9/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDuplicate content in training data can cause model memorization and performance degradation.76% similarUnverified当生成模型反复在自身生成的数据上训练时，输出分布会逐渐退化，低概率事件被系统性遗忘74% similarUnverifiedThe 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.74% 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72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/860365API
curl https://kongchang.com/api/v1/knowledge/claims/860365MCP
get_claim(id=860365)