Timezone: »

PAL: Program-aided Language Models
Luyu Gao · Aman Madaan · Shuyan Zhou · Uri Alon · Pengfei Liu · Yiming Yang · Jamie Callan · Graham Neubig

Tue Jul 25 05:00 PM -- 06:30 PM (PDT) @ Exhibit Hall 1 #732
Event URL: https://reasonwithpal.com »

Large language models (LLMs) have demonstrated an impressive ability to perform arithmetic and symbolic reasoning tasks, when provided with a few examples at test time ("few-shot prompting"). Much of this success can be attributed to prompting methods such as "chain-of-thought", which employ LLMs for both understanding the problem description by decomposing it into steps, as well as solving each step of the problem. While LLMs seem to be adept at this sort of step-by-step decomposition, LLMs often make logical and arithmetic mistakes in the solution part, even when the problem is decomposed correctly. In this paper, we present Program-Aided Language models (PAL): a novel approach that uses the LLM to read natural language problems and generate programs as the intermediate reasoning steps, but offloads the solution step to a runtime such as a Python interpreter. With PAL, decomposing the natural language problem into runnable steps remains the only learning task for the LLM, while solving is delegated to the interpreter. We demonstrate this synergy between a neural LLM and a symbolic interpreter across 13 mathematical, symbolic, and algorithmic reasoning tasks from BIG-Bench Hard and others. In all these natural language reasoning tasks, generating code using an LLM and reasoning using a Python interpreter leads to more accurate results than much larger models. For example, PAL using Codex achieves state-of-the-art few-shot accuracy on GSM8K, surpassing PaLM which uses chain-of-thought by absolute 15% top-1.

Author Information

Luyu Gao
Aman Madaan (Carnegie Mellon University)
Shuyan Zhou (Carnegie Mellon University)
Uri Alon (Carnegie Mellon University)
Pengfei Liu (Carnegie Mellon University)
Yiming Yang (Carnegie Mellon University)
Jamie Callan (Carnegie Mellon University)
Graham Neubig (Carnegie Mellon University)

More from the Same Authors