Best of Both Worlds: A Hybrid Approach for Multi-Hop Explanation with Declarative Facts

TL;DR

This paper presents a hybrid approach combining syntactic and semantic methods to generate multi-hop explanations from declarative facts, improving efficiency and accuracy for AI transparency.

Contribution

It introduces a lightweight reasoning operation and fine-tuning strategy that outperforms previous syntactic baselines in explanation retrieval.

Findings

Up to 7% improvement in explanation retrieval rate

Effective integration of fast syntactic and semantic methods

Enhanced transparency and trustworthiness in AI explanations

Abstract

Language-enabled AI systems can answer complex, multi-hop questions to high accuracy, but supporting answers with evidence is a more challenging task which is important for the transparency and trustworthiness to users. Prior work in this area typically makes a trade-off between efficiency and accuracy; state-of-the-art deep neural network systems are too cumbersome to be useful in large-scale applications, while the fastest systems lack reliability. In this work, we integrate fast syntactic methods with powerful semantic methods for multi-hop explanation generation based on declarative facts. Our best system, which learns a lightweight operation to simulate multi-hop reasoning over pieces of evidence and fine-tunes language models to re-rank generated explanation chains, outperforms a purely syntactic baseline from prior work by up to 7% in gold explanation retrieval rate.