CORRPUS: Code-based Structured Prompting for Neurosymbolic Story Understanding
Links to Files
Author/Creator
Author/Creator ORCID
Date
Type of Work
Department
Program
Citation of Original Publication
Yijiang Dong, Lara Martin, and Chris Callison-Burch. 2023. CoRRPUS: Code-based Structured Prompting for Neurosymbolic Story Understanding. In Findings of the Association for Computational Linguistics: ACL 2023, pages 13152–13168, Toronto, Canada. Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.findings-acl.832
Rights
This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
Attribution 4.0 International (CC BY 4.0)
Attribution 4.0 International (CC BY 4.0)
Subjects
Abstract
Story generation and understanding—as with
all NLG/NLU tasks—has seen a surge in neurosymbolic work. Researchers have recognized
that, while large language models (LLMs) have
tremendous utility, they can be augmented
with symbolic means to be even better and
to make up for many flaws that neural networks have. However, symbolic methods are
extremely costly in terms of the amount of time
and expertise needed to create them. In this
work, we capitalize on state-of-the-art CodeLLMs, such as Codex, to bootstrap the use
of symbolic methods for tracking the state of
stories and aiding in story understanding. We
show that our CoRRPUS system and abstracted
prompting procedures can beat current stateof-the-art structured LLM techniques on preexisting story understanding tasks (bAbI Task 2
and Re³
) with minimal hand engineering. This
work highlights the usefulness of code-based
symbolic representations for enabling LLMs to
better perform story reasoning tasks.