Interpretable Proof Generation via Iterative Backward Reasoning

TL;DR

The paper introduces IBR, an iterative backward reasoning model that improves interpretability, efficiency, and accuracy in proof generation for rule-based question answering by tracking proof paths and reasoning on detailed representations.

Contribution

It proposes a novel IBR model that enhances interpretability and transferability in proof generation through iterative backward reasoning and detailed node and path representations.

Findings

IBR outperforms strong baselines in in-domain tasks.

IBR demonstrates superior cross-domain transferability.

The model effectively tracks proof paths with detailed reasoning.

Abstract

We present IBR, an Iterative Backward Reasoning model to solve the proof generation tasks on rule-based Question Answering (QA), where models are required to reason over a series of textual rules and facts to find out the related proof path and derive the final answer. We handle the limitations of existed works in two folds: 1) enhance the interpretability of reasoning procedures with detailed tracking, by predicting nodes and edges in the proof path iteratively backward from the question; 2) promote the efficiency and accuracy via reasoning on the elaborate representations of nodes and history paths, without any intermediate texts that may introduce external noise during proof generation. There are three main modules in IBR, QA and proof strategy prediction to obtain the answer and offer guidance for the following procedure; parent node prediction to determine a node in the existing proof that a new child node will link to; child node prediction to find out which new node will be added to the proof. Experiments on both synthetic and paraphrased datasets demonstrate that IBR has better in-domain performance as well as cross-domain transferability than several strong baselines. Our code and models are available at https://github.com/find-knowledge/IBR .