Knowledge-enhanced Iterative Instruction Generation and Reasoning for Knowledge Base Question Answering

TL;DR

This paper introduces KBIGER, a dynamic instruction generation method for multi-hop KBQA that iteratively revises reasoning errors by considering the reasoning graph, leading to state-of-the-art results.

Contribution

Proposes KBIGER, a novel approach that generates instructions dynamically using reasoning graphs, enabling error correction during multi-hop question answering.

Findings

Outperforms existing methods on two benchmarks.

Effectively detects and revises intermediate entity prediction errors.

Achieves new state-of-the-art performance.

Abstract

Multi-hop Knowledge Base Question Answering(KBQA) aims to find the answer entity in a knowledge base which is several hops from the topic entity mentioned in the question. Existing Retrieval-based approaches first generate instructions from the question and then use them to guide the multi-hop reasoning on the knowledge graph. As the instructions are fixed during the whole reasoning procedure and the knowledge graph is not considered in instruction generation, the model cannot revise its mistake once it predicts an intermediate entity incorrectly. To handle this, we propose KBIGER(Knowledge Base Iterative Instruction GEnerating and Reasoning), a novel and efficient approach to generate the instructions dynamically with the help of reasoning graph. Instead of generating all the instructions before reasoning, we take the (k-1)-th reasoning graph into consideration to build the k-th instruction. In this way, the model could check the prediction from the graph and generate new instructions to revise the incorrect prediction of intermediate entities. We do experiments on two multi-hop KBQA benchmarks and outperform the existing approaches, becoming the new-state-of-the-art. Further experiments show our method does detect the incorrect prediction of intermediate entities and has the ability to revise such errors.