Learning to Retrieve and Reason on Knowledge Graph through Active Self-Reflection

TL;DR

This paper introduces an active self-reflection framework for knowledge graph reasoning that enables iterative, interpretable reasoning paths, improving performance over existing methods by incorporating reflection and active retrieval.

Contribution

The paper presents the first end-to-end training approach for iterative reasoning on knowledge graphs using active self-reflection, enhancing interpretability and reasoning accuracy.

Findings

Achieves superior results on knowledge graph reasoning tasks

Provides high interpretability of reasoning paths

Enables iterative reflection and correction during reasoning

Abstract

Extensive research has investigated the integration of large language models (LLMs) with knowledge graphs to enhance the reasoning process. However, understanding how models perform reasoning utilizing structured graph knowledge remains underexplored. Most existing approaches rely on LLMs or retrievers to make binary judgments regarding the utilization of knowledge, which is too coarse. Meanwhile, there is still a lack of feedback mechanisms for reflection and correction throughout the entire reasoning path. This paper proposes an Active self-Reflection framework for knowledge Graph reasoning ARG, introducing for the first time an end-to-end training approach to achieve iterative reasoning grounded on structured graphs. Within the framework, the model leverages special tokens to \textit{actively} determine whether knowledge retrieval is necessary, performs \textit{reflective} critique based on the retrieved knowledge, and iteratively reasons over the knowledge graph. The reasoning paths generated by the model exhibit high interpretability, enabling deeper exploration of the model's understanding of structured knowledge. Ultimately, the proposed model achieves outstanding results compared to existing baselines in knowledge graph reasoning tasks.