Unverified60% confidenceFactExact time
The CFG value (Classifier-Free Guidance Scale) controls the degree to which the model adheres to the prompt; a higher value yields greater fidelity but may result in oversaturation.
2
Sources
60%
Confidence
Long-term
Relevance
8/24/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedClassifier-Free Guidance technology allows the model to adjust the degree to which it follows the prompt; the higher the guidance strength, the closer the result is to the text description, but excessively high values can cause oversaturated colors and distorted details.73% similarUnverifiedClassifier-Free Guidance balances generation quality and conditional consistency by randomly dropping condition information during training and adjusting the guidance scale during inference.73% similarUnverifiedAlignment training typically includes large amounts of demonstration data such as "refusing harmful requests" and "stating one's own limitations," which makes models inclined to produce safety-compliant statements at the text level, but this text-level alignment does not automatically transfer to the action level.68% similarUnverifiedIn behavior-constrained reinforcement learning, KL regularization can be achieved with access only to the gradient of the reference policy, and the gradient of the reference policy can be obtained through a velocity score transformation.67% similarUnverifiedThe core idea of inoculation prompting is: if the model is told before training that the behavior is acceptable, then the association between the behavior and misalignment will not be established, thereby blocking the generalization of misalignment; unlike SDF, inoculation prompting is given directly in the form of a system prompt during RL training and involves no parameter updates, so its coverage strength is higher.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/793909API
curl https://kongchang.com/api/v1/knowledge/claims/793909MCP
get_claim(id=793909)