Knowledge Graph Question Answering

Also known as KGQA

Overview

Knowledge Graph Question Answering (KGQA) connects questions to entities and relations in a graph, then returns answers supported by its structured facts. Common approaches translate questions into SPARQL or logical forms, retrieve and traverse multi-hop paths, or combine graph neural networks and symbolic rules with large language models and retrieval-augmented generation. Benchmarks such as WebQSP, ComplexWebQuestions, and GrailQA test query execution, compositional reasoning, and generalization, while newer evaluations examine temporal, biomedical, and incomplete-graph settings. A central challenge is ensuring that answers are both accurate and grounded in relevant evidence, especially when graphs are sparse or noisy and benchmark questions may not require genuine multi-hop reasoning.

Latest papers

182 papers19 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

Feb 17, 2025

Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering

Large language models (LLMs) have shown remarkable capabilities in natural language processing. However, in knowledge graph question answering tasks (KGQA), there remains the issue of answering questions that require multi-hop reasoning. Existing methods rely on entity vector matching, but the purpose of the question is abstract and difficult to match with specific entities. As a result, it is difficult to establish reasoning paths to the purpose, which leads to information loss and redundancy. To address this issue, inspired by human reverse thinking, we propose Ontology-Guided Reverse Thinking (ORT), a novel framework that constructs reasoning paths from purposes back to conditions. ORT operates in three key phases: (1) using LLM to extract purpose labels and condition labels, (2) constructing label reasoning paths based on the KG ontology, and (3) using the label reasoning paths to guide knowledge retrieval. Experiments on the WebQSP and CWQ datasets show that ORT achieves state-of-the-art performance and significantly enhances the capability of LLMs for KGQA.
Oct 16, 2024

Is Complex Query Answering Really Complex?

Complex query answering (CQA) on knowledge graphs (KGs) is gaining momentum as a challenging reasoning task. In this paper, we show that the current benchmarks for CQA might not be as complex as we think, as the way they are built distorts our perception of progress in this field. For example, we find that in these benchmarks, most queries (up to 98% for some query types) can be reduced to simpler problems, e.g., link prediction, where only one link needs to be predicted. The performance of state-of-the-art CQA models decreases significantly when such models are evaluated on queries that cannot be reduced to easier types. Thus, we propose a set of more challenging benchmarks composed of queries that require models to reason over multiple hops and better reflect the construction of real-world KGs. In a systematic empirical investigation, the new benchmarks show that current methods leave much to be desired from current CQA methods.