Generating Intermediate Steps for NLI with Next-Step Supervision

TL;DR

This paper introduces a method for generating intermediate reasoning steps in NLI tasks using next-step supervision, external knowledge, and symbolic search, which improves overall NLI performance.

Contribution

It presents a novel approach to generate intermediate reasoning steps without full supervision, enhancing NLI accuracy through data augmentation.

Findings

Generated steps are verified as correct by humans and automated methods.

Using generated steps improves NLI performance across multiple datasets.

The approach effectively leverages external knowledge and symbolic search.

Abstract

The Natural Language Inference (NLI) task often requires reasoning over multiple steps to reach the conclusion. While the necessity of generating such intermediate steps (instead of a summary explanation) has gained popular support, it is unclear how to generate such steps without complete end-to-end supervision and how such generated steps can be further utilized. In this work, we train a sequence-to-sequence model to generate only the next step given an NLI premise and hypothesis pair (and previous steps); then enhance it with external knowledge and symbolic search to generate intermediate steps with only next-step supervision. We show the correctness of such generated steps through automated and human verification. Furthermore, we show that such generated steps can help improve end-to-end NLI task performance using simple data augmentation strategies, across multiple public NLI datasets.