Best of Both Worlds: A Hybrid Approach for Multi-Hop Explanation with Declarative Facts
This work addresses the problem of providing transparent and trustworthy evidence for complex AI answers, which is incremental as it combines existing approaches to improve efficiency and accuracy.
The paper tackles the challenge of generating multi-hop explanations for AI answers by integrating fast syntactic methods with powerful semantic methods, resulting in a hybrid system that outperforms a purely syntactic baseline by up to 7% in gold explanation retrieval rate.
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.