KGQuest: Template-Driven QA Generation from Knowledge Graphs with LLM-Based Refinement
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917080214798336 |
|---|---|
| author | Nayab, Sania Simoni, Marco Rossolini, Giulio Saracino, Andrea |
| author_facet | Nayab, Sania Simoni, Marco Rossolini, Giulio Saracino, Andrea |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_11258 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | KGQuest: Template-Driven QA Generation from Knowledge Graphs with LLM-Based Refinement Nayab, Sania Simoni, Marco Rossolini, Giulio Saracino, Andrea Computation and Language Artificial Intelligence 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. |
| title | KGQuest: Template-Driven QA Generation from Knowledge Graphs with LLM-Based Refinement |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2511.11258 |