Unverified50% confidenceConceptExact time
A decision head is a small classification or scoring module trained on top of a backbone model, computing scores for each option directly from the context representation, obtaining a probability distribution via softmax, and outputting an option rather than generating token by token.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe decision head is an additional output layer outside the model backbone, typically receiving the feature vector extracted by the backbone and outputting a judgment result or score.77% similarUnverifiedDecisionLoop is a Python framework that decouples an Agent's decision layer (intent recognition, tool selection, parameter generation, process control) from the language layer, with the decision layer handled by a small decision model and the language layer handled by an LLM for natural language understanding and generation.76% similarUnverifiedThe Decisions API is a classification decision tool with no output tokens that makes fast, intelligent selections from preset options, corresponding to the classifier paradigm in machine learning rather than a generative model.74% similarUnverifiedThe Typed Decisions benchmark is a structured, probabilistic classification benchmark that specifically measures a model's ability to make calibrated decisions in multi-dimensional classification tasks.73% similarUnverifiedA decision model is a type of model designed specifically for making choices among a limited set of options, with output constrained to a predefined structure, and its fundamental difference from generative models lies in the output space.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1048440API
curl https://kongchang.com/api/v1/knowledge/claims/1048440MCP
get_claim(id=1048440)