Probabilistic Programs of Thought

TL;DR

This paper introduces a novel framework called probabilistic programs of thought that enables more efficient sampling of programs from large language models by leveraging probabilistic reasoning, reducing computational costs.

Contribution

It presents a new test-time method to represent and sample multiple programs efficiently using probabilistic programming, improving performance with fewer model generations.

Findings

Achieves better performance on code generation, understanding, and reasoning benchmarks.

Reduces the number of costly LLM generations needed for sampling.

Demonstrates significant computational savings with maintained or improved accuracy.

Abstract

LLMs are widely used for code generation and mathematical reasoning tasks where they are required to generate structured output. They either need to reason about code, generate code for a given specification, or reason using programs of thought. The typical approach to code generation is to prompt the model and generate samples until an appropriate program is obtained. Within this process, sampling $n$ programs from the language model requires $n$ GPU compute-intensive generations which becomes prohibitively expensive for larger values of $n$. In this work, we address this limitation by exposing the LLM's distribution within the generated programs themselves. We propose a novel test-time framework we dub probabilistic programs of thought to obtain more samples from the model with fewer LLM generations. Given a program generated by a model and the associated next-token probabilities, we build a probabilistic program that compactly represents exponentially many deterministic programs. Since performing probabilistic reasoning in this probabilistic program is much cheaper, our approach allows sampling new programs without any additional GPU compute and little CPU overhead. We instantiate our approach on benchmarks for code generation, code understanding and mathematical reasoning and report improvements in performance with fewer generations from the LLM.