CoRRPUS: Code-based Structured Prompting for Neurosymbolic Story Understanding

TL;DR

This paper introduces CoRRPUS, a code-based structured prompting approach that leverages Code-LLMs to enhance neurosymbolic story understanding, outperforming current methods with minimal manual engineering.

Contribution

The work demonstrates how to effectively use Code-LLMs with structured prompts to improve story understanding, highlighting the value of symbolic reasoning in large language models.

Findings

Outperforms state-of-the-art structured LLM techniques on story understanding tasks

Requires minimal hand engineering for effective performance

Highlights the importance of symbolic representations and specialized prompting

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.