Unverified50% confidenceFactExact time
Compared with the approach of directly applying supervised fine-tuning (SFT) followed by reinforcement learning, the rubric-guided method performs better.
1
Sources
50%
Confidence
Long-term
Relevance
11/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe paper's experiments show that supervised fine-tuning (SFT) can make preferences learnable.80% similarUnverifiedApplying 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.77% similarUnverifiedThe study compared standard methods, including supervised fine-tuning (SFT), GRPO, and gradient ascent unlearning.76% similarUnverifiedSupervised fine-tuning (SFT) optimizes imitation loss rather than a behavioral safety objective, so it readily exhibits the phenomenon of "working within the training distribution but failing out of distribution."75% 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.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1138254API
curl https://kongchang.com/api/v1/knowledge/claims/1138254MCP
get_claim(id=1138254)