Unverified50% confidenceFactExact time
The study compared standard methods, including supervised fine-tuning (SFT), GRPO, and gradient ascent unlearning.
1
Sources
50%
Confidence
Long-term
Relevance
11/4/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe paper's experiments show that supervised fine-tuning (SFT) can make preferences learnable.78% similarUnverifiedExperimental results show that SAPD improves performance under different teacher configurations and effectively mitigates catastrophic forgetting compared with SFT.74% similarUnverifiedA contemporaneous study by O'Brien et al. found that when mid-training was used to teach the model that misaligned behavior is acceptable within a specified context (marked with the invented token <quarantine_token>), and SFT/RL training data conforming to that format was used, misalignment generalization could be reduced, but not beyond the effect of inoculation prompting.70% similarUnverifiedSFT is usually much cheaper than pretraining but is extremely sensitive to data quality; data ratios, the number of epochs, and the learning rate all significantly affect results.70% similarVerified从预训练检查点到可商用产品需经历监督式指令微调（SFT）和基于人类反馈的强化学习（RLHF）两个后训练阶段70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1134232API
curl https://kongchang.com/api/v1/knowledge/claims/1134232MCP
get_claim(id=1134232)