Unverified50% confidenceBenchmarkExact time
Experimental results show that SAPD improves performance under different teacher configurations and effectively mitigates catastrophic forgetting compared with SFT.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/21/2026
First Seen
Valid until: 1/19/2027
Sources
Related Entities
Related Claims
UnverifiedApplying reinforcement learning starting from a repaired SFT checkpoint yields larger and more stable performance gains, indicating a synergistic effect between repairing first and reinforcing afterward.68% similarUnverifiedThe paper's experiments show that supervised fine-tuning (SFT) can make preferences learnable.64% similarUnverifiedOPRD's teacher and student share the same two-stage initialization: first Coding SFT, then Instruction-Following SFT.62% similarUnverifiedUsing real pre-trained PLE performs significantly better than control groups using random memory and shuffled memory.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1079161API
curl https://kongchang.com/api/v1/knowledge/claims/1079161MCP
get_claim(id=1079161)