Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning

TL;DR

This paper introduces a Selection-Inference framework that enhances large language models' ability to perform multi-step logical reasoning, producing interpretable causal reasoning traces and significantly improving performance without fine-tuning.

Contribution

The paper proposes a novel Selection-Inference framework that leverages pre-trained LLMs for interpretable, multi-step logical reasoning, outperforming larger models and baseline methods without additional training.

Findings

7B LLM with SI outperforms vanilla baseline by over 100% on logical tasks.

SI framework produces interpretable causal reasoning traces.

Model even surpasses 280B parameter models in performance.

Abstract

Large language models (LLMs) have been shown to be capable of impressive few-shot generalisation to new tasks. However, they still tend to perform poorly on multi-step logical reasoning problems. Here we carry out a comprehensive evaluation of LLMs on 50 tasks that probe different aspects of logical reasoning. We show that language models tend to perform fairly well at single step inference or entailment tasks, but struggle to chain together multiple reasoning steps to solve more complex problems. In light of this, we propose a Selection-Inference (SI) framework that exploits pre-trained LLMs as general processing modules, and alternates between selection and inference to generate a series of interpretable, casual reasoning steps leading to the final answer. We show that a 7B parameter LLM used within the SI framework in a 5-shot generalisation setting, with no fine-tuning, yields a performance improvement of over 100% compared to an equivalent vanilla baseline on a suite of 10 logical reasoning tasks. The same model in the same setting even outperforms a significantly larger 280B parameter baseline on the same suite of tasks. Moreover, answers produced by the SI framework are accompanied by a causal natural-language-based reasoning trace, which has important implications for the safety and trustworthiness of the system.