UniRel: Relation-Centric Knowledge Graph Question Answering with RL-Tuned LLM Reasoning
This addresses a complementary setting in knowledge graph question answering for users needing relational insights, though it is incremental as it builds on existing methods with modular enhancements.
The paper tackles the problem of relation-centric knowledge graph question answering, where answers are subgraphs representing semantic relations among entities, by proposing UniRel, a framework combining subgraph retrieval with a reinforcement learning-tuned large language model, which improves connectivity and reward over baselines and generalizes to unseen entities and relations.
Knowledge Graph Question Answering (KGQA) has largely focused on entity-centric queries that return a single answer entity. However, many real-world questions are inherently relational, aiming to understand how entities are associated rather than which entity satisfies a query. In this work, we introduce relation-centric KGQA, a complementary setting in which the answer is a subgraph that represents the semantic relations among entities. The main challenge lies in the abundance of candidate subgraphs, where trivial or overly common connections often obscure the identification of unique and informative answers. To tackle this, we propose UniRel, a unified modular framework that combines a subgraph retriever with an LLM fine-tuned using reinforcement learning. The framework uses a reward function to prefer compact and specific subgraphs with informative relations and low-degree intermediate entities. Experiments show that UniRel improves connectivity and reward over Prompting baselines and generalizes well to unseen entities and relations. Moreover, UniRel can be applied to conventional entity-centric KGQA, achieving competitive or improved performance in several settings.