Neuro-Symbolic Procedural Planning with Commonsense Prompting

Understand

Procedural planning aims to implement complex high-level goals by decomposition into sequential simpler low-level steps.

• Although procedural planning is a basic skill set for humans in daily life, it remains a challenge for large language models (LLMs) that lack a deep understanding of the cause-effect relations in procedures.
• Previous methods require manual exemplars to acquire procedural planning knowledge from LLMs in the zero-shot setting.
• However, such elicited pre-trained knowledge in LLMs induces spurious correlations between goals and steps, which impair the model generalization to unseen tasks.