Unverified50% confidenceFactExact time
Supervised fine-tuning (SFT) tends to cause more severe catastrophic forgetting than reinforcement fine-tuning (RFT).
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSFT fine-tuning is effective but causes a decline in general knowledge in small models—i.e., the phenomenon of catastrophic forgetting—due to the prominent capacity bottleneck of small models.77% similarUnverified多头自注意力机制突破了RNN/LSTM在长序列处理中因梯度消失导致的遗忘瓶颈，并支持GPU/TPU大规模并行计算70% similarUnverifiedExcessively thorough SFT may harm the exploration space for subsequent RL, and a perfectly converged SFT model is not necessarily the best starting point for RL.67% similarUnverifiedThe paper proves that starting from the same perfectly fitted checkpoint, SFT's forgetting over a finite training interval has a lower bound that is strictly greater than zero.66% similarUnverified在监督微调（SFT）中，数据的分布往往比数据的数量更关键，精准的数据补充胜过盲目扩充数据集65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/975961API
curl https://kongchang.com/api/v1/knowledge/claims/975961MCP
get_claim(id=975961)