Unverified50% confidenceFactExact time
Constrained decoding relies on finite state machines (FSM) or pushdown automata to express the complete set of valid outputs, pre-compiling the schema into a state transition graph.
1
Sources
50%
Confidence
Long-term
Relevance
9/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOutlines pre-compiles constraints into an FSM before inference, and offline-maps the tokenizer's complete vocabulary to each FSM state to generate an index table of valid token sets per state.80% similarUnverifiedThe underlying implementation of constrained decoding relies on finite state machines (FSM) or context-free grammars (CFG).77% similarUnverifiedStructured output applies constraints to the model's token sampling via constrained decoding, typically based on finite-state automata (FSA) or context-free grammars (CFG).76% similarUnverifiedOutlines pre-compiles constraints into an FSM before inference and performs an offline mapping between the tokenizer vocabulary and each state of the FSM; during inference, hard constraints are enforced by setting the logits of illegal tokens to negative infinity (logits masking).70% similarUnverifiedOutlines 通过将正则表达式和 JSON Schema 编译为有限状态机（FSM），再映射到 LLM 分词器的词表空间来实现约束68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/928849API
curl https://kongchang.com/api/v1/knowledge/claims/928849MCP
get_claim(id=928849)