Unverified50% confidenceOpinionExact time
Through truncation and rationale augmentation, JET essentially introduces an emphasis on key decisions within the SFT framework, thereby alleviating SFT's shortcomings.
1
Sources
50%
Confidence
Long-term
Relevance
11/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSupervised fine-tuning (SFT) tends to cause more severe catastrophic forgetting than reinforcement fine-tuning (RFT).63% similarUnverifiedThe JET method truncates training trajectories: it stops at the step where information becomes sufficient and inserts a rationale explaining why to stop.60% 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.60% similarUnverifiedFuture directions for Ambient SFT may extend to more modalities and tasks, or combine with parameter-efficient fine-tuning techniques to further lower the barrier to fine-tuning.59% similarUnverifiedSFT 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.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1182983API
curl https://kongchang.com/api/v1/knowledge/claims/1182983MCP
get_claim(id=1182983)