CoRRPUS: Code-based Structured Prompting for Neurosymbolic Story Understanding

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 any flaws that the neural networks might 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 Re^3) with minimal hand engineering. We hope that this work can help highlight the importance of symbolic representations and specialized prompting for LLMs as these models require some guidance for performing reasoning tasks properly.

Accepted to Findings of ACL 2023

References in corpus (10)

• Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
• Evaluating Large Language Models Trained on Code
• Self-Consistency Improves Chain of Thought Reasoning in Language Models
• Scaling Language Models: Methods, Analysis & Insights from Training Gopher
• Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning
• Neurosymbolic AI: The 3rd Wave
• Autoformalization with Large Language Models
• Goal-Directed Story Generation: Augmenting Generative Language Models with Reinforcement Learning
• Summarize, Outline, and Elaborate: Long-Text Generation via Hierarchical Supervision from Extractive Summaries
• Language Models of Code are Few-Shot Commonsense Learners