Automaton-Based Representations of Task Knowledge from Generative Language Models. (arXiv:2212.01944v5 [cs.FL] UPDATED)

Automaton-based representations of task knowledge play an important role in
control and planning for sequential decision-making problems. However,
obtaining the high-level task knowledge required to build such automata is
often difficult. Meanwhile, large-scale generative language models (GLMs) can
automatically generate relevant task knowledge. However, the textual outputs
from GLMs cannot be formally verified or used for sequential decision-making.
We propose a novel algorithm named GLM2FSA, which constructs a finite state
automaton (FSA) encoding high-level task knowledge from a brief
natural-language …

arxiv automaton build control decision generative knowledge language language models making planning role scale textual