{"type":"ScholarlyArticle","title":"R2DQG: A Quality Meets Diversity Framework for Question Generation over Knowledge Bases","authors":[{"name":"Yimeng Ren","slug":"yimeng-ren","given":"Yimeng","family":"Ren","affiliation":""},{"name":"Yanhua Yu","slug":"yanhua-yu","given":"Yanhua","family":"Yu","affiliation":""},{"name":"Lizi Liao","slug":"lizi-liao","given":"Lizi","family":"Liao","affiliation":""},{"name":"Yuhu Shang","slug":"yuhu-shang","given":"Yuhu","family":"Shang","affiliation":""},{"name":"Kangkang Lu","slug":"kangkang-lu","given":"Kangkang","family":"Lu","affiliation":""},{"name":"Mingliang Yan","slug":"mingliang-yan","given":"Mingliang","family":"Yan","affiliation":""}],"abstract":"The task of Knowledge-Based Question Generation (KBQG) involves generating natural language questions from structured knowledge sources, posing unique challenges in balancing linguistic diversity and semantic relevance. Existing models often focus on maximizing surface-level similarity to ground-truth questions, neglecting the need for diverse syntactic forms and leading to semantic drift during generation. To overcome these challenges, we propose Refine-Reinforced Diverse Question Generation (R2DQG), a two-phase framework leveraging a generation-then-refinement paradigm. The Generator first constructs a diverse set of expressive templates using dependency parse tree similarity, capturing a wide range of syntactic patterns and styles. These templates guide the creation of question drafts, ensuring both diversity and semantic relevance. In the second phase, a Corrector module refines the drafts to mitigate semantic drift and enhance overall coherence and quality. Experiments on public datasets show that R2DQG outperforms state-of-the-art models in generating diverse, contextually accurate questions. Moreover, synthetic datasets generated by R2DQG enhance downstream QA performance, underscoring the practical utility of our approach.","doi":"10.24963/ijcai.2025/915","url":"https://ijcai.org/proceedings/2025/915","pdf":"https://ijcai.org/proceedings/2025/0915.pdf","markdown":"https://ijcai.org/proceedings/2025/915.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/915","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Natural Language Processing","track":"Main Track","number":915,"pages":{"first":8231,"last":8240},"keywords":["Natural Language Processing: NLP: Question answering","Data Mining: DM: Knowledge graphs and knowledge base completion","Natural Language Processing: NLP: Language generation","Natural Language Processing: NLP: Summarization"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}