Unverified50% confidenceOpinionExact time
Token-probability-based supervision (such as KL divergence) is simple, but the teacher's output probability distribution often only reflects relative preferences near the decision boundary and underuses the rich internal semantic representations.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedReverse KL divergence tends to make the student focus on a few high-probability modes of the teacher (mode-seeking), and when the teacher has a sharper, more trustworthy distribution because it carries the Reminder, it is more suitable as the correction target for failed rollouts.78% similarVerifiedBehavioral cloning simplifies the problem to supervised learning, but suffers from distribution shift, where differences between the state distributions at training time and execution time lead to error accumulation.72% similarUnverifiedWhen out-of-distribution (OOD) failure occurs, learned selectors may persistently ignore key evidence, resulting in answers that appear fluent but omit key facts, increasing the difficulty of troubleshooting.69% similarUnverifiedStandardized benchmarks have the limitation of out-of-distribution generalization, where agents may score by memorizing training set patterns rather than truly possessing reasoning ability.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1069443API
curl https://kongchang.com/api/v1/knowledge/claims/1069443MCP
get_claim(id=1069443)