Generating Intermediate Steps for NLI with Next-Step Supervision
This work addresses the challenge of multi-step reasoning in NLI for AI and NLP researchers, offering a method to generate steps with limited supervision, though it is incremental as it builds on existing sequence-to-sequence and knowledge integration techniques.
The authors tackled the problem of generating intermediate reasoning steps for Natural Language Inference (NLI) without full supervision, by training a model with next-step supervision and enhancing it with external knowledge and symbolic search, resulting in improved NLI task performance across multiple datasets.
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.