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 Code-LLMs, 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 state-of-the-art structured LLM techniques on pre-existing 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.- Anthology ID:
- 2023.findings-acl.832
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2023
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 13152–13168
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.832
- DOI:
- 10.18653/v1/2023.findings-acl.832
- Cite (ACL):
- Yijiang River Dong, Lara J. 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.
- Cite (Informal):
- CoRRPUS: Code-based Structured Prompting for Neurosymbolic Story Understanding (Dong et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2023.findings-acl.832.pdf