Parsel: A (De-)compositional Framework for Algorithmic Reasoning with Language Models
Despite recent success in large language model (LLM) reasoning, LLMs struggle with hierarchical multi-step reasoning tasks like generating complex programs. For these tasks, humans often start with a high-level algorithmic design and implement each part gradually. We introduce Parsel, a framework enabling automatic implementation and validation of complex algorithms with code LLMs, taking hierarchical function descriptions in natural language as input. We show that Parsel can be used across domains requiring hierarchical reasoning, including program synthesis, robotic planning, and theorem proving. We show that LLMs generating Parsel solve more competition-level problems in the APPS dataset, resulting in pass rates that are over 75% higher than prior results from directly sampling AlphaCode and Codex, while often using a smaller sample budget. We also find that LLM-generated robotic plans using Parsel as an intermediate language are more than twice as likely to be considered accurate than directly generated plans. Lastly, we explore how Parsel addresses LLM limitations and discuss how Parsel may be useful for human programmers.
PDF AbstractCode
Datasets
APPS
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Code Generation | APPS | Parsel (w/ Codex) | Competition Pass@any | 25.5% | # 1 |
