ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph

TL;DR

ReasoningLM is a novel pre-trained language model designed to perform direct subgraph reasoning in knowledge graph question answering, improving accuracy and efficiency over previous multi-module approaches.

Contribution

The paper introduces ReasoningLM, a PLM with a subgraph-aware self-attention mechanism and adaptation tuning, enabling integrated structured reasoning for KGQA.

Findings

Surpasses state-of-the-art models in accuracy

Requires fewer parameters and less training data

Demonstrates effective structured reasoning capabilities

Abstract

Question Answering over Knowledge Graph (KGQA) aims to seek answer entities for the natural language question from a large-scale Knowledge Graph~(KG). To better perform reasoning on KG, recent work typically adopts a pre-trained language model~(PLM) to model the question, and a graph neural network~(GNN) based module to perform multi-hop reasoning on the KG. Despite the effectiveness, due to the divergence in model architecture, the PLM and GNN are not closely integrated, limiting the knowledge sharing and fine-grained feature interactions. To solve it, we aim to simplify the above two-module approach, and develop a more capable PLM that can directly support subgraph reasoning for KGQA, namely ReasoningLM. In our approach, we propose a subgraph-aware self-attention mechanism to imitate the GNN for performing structured reasoning, and also adopt an adaptation tuning strategy to adapt the model parameters with 20,000 subgraphs with synthesized questions. After adaptation, the PLM can be parameter-efficient fine-tuned on downstream tasks. Experiments show that ReasoningLM surpasses state-of-the-art models by a large margin, even with fewer updated parameters and less training data. Our codes and data are publicly available at~\url{https://github.com/RUCAIBox/ReasoningLM}.