English

Interactive Learning of Hierarchical Tasks from Dialog with GPT

Human-Computer Interaction 2023-05-18 v1 Artificial Intelligence Computation and Language

Abstract

We present a system for interpretable, symbolic, interactive task learning from dialog using a GPT model as a conversational front-end. The learned tasks are represented as hierarchical decompositions of predicate-argument structures with scoped variable arguments. By using a GPT model to convert interactive dialog into a semantic representation, and then recursively asking for definitions of unknown steps, we show that hierarchical task knowledge can be acquired and re-used in a natural and unrestrained conversational environment. We compare our system to a similar architecture using a more conventional parser and show that our system tolerates a much wider variety of linguistic variance.

Keywords

Cite

@article{arxiv.2305.10349,
  title  = {Interactive Learning of Hierarchical Tasks from Dialog with GPT},
  author = {Lane Lawley and Christopher J. MacLellan},
  journal= {arXiv preprint arXiv:2305.10349},
  year   = {2023}
}

Comments

5 pages, 3 figures

R2 v1 2026-06-28T10:37:19.041Z