KGQuest: Template-Driven QA Generation from Knowledge Graphs with LLM-Based Refinement
This work addresses the need for scalable and linguistically accurate QA generation for educational platforms and LLM testing, though it is incremental as it builds on existing template and LLM methods.
The paper tackled the problem of generating questions and answers from knowledge graphs, which often suffer from scalability and quality issues, by proposing a template-driven pipeline with LLM-based refinement, resulting in efficient production of high-quality QA pairs with improved fluency and precision.
The generation of questions and answers (QA) from knowledge graphs (KG) plays a crucial role in the development and testing of educational platforms, dissemination tools, and large language models (LLM). However, existing approaches often struggle with scalability, linguistic quality, and factual consistency. This paper presents a scalable and deterministic pipeline for generating natural language QA from KGs, with an additional refinement step using LLMs to further enhance linguistic quality. The approach first clusters KG triplets based on their relations, creating reusable templates through natural language rules derived from the entity types of objects and relations. A module then leverages LLMs to refine these templates, improving clarity and coherence while preserving factual accuracy. Finally, the instantiation of answer options is achieved through a selection strategy that introduces distractors from the KG. Our experiments demonstrate that this hybrid approach efficiently generates high-quality QA pairs, combining scalability with fluency and linguistic precision.