Generate-Then-Validate: A Novel Question Generation Approach Using Small Language Models
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_ | 1866918292379140096 |
|---|---|
| author | Wei, Yumou Stamper, John Carvalho, Paulo F. |
| author_facet | Wei, Yumou Stamper, John Carvalho, Paulo F. |
| contents | We explore the use of small language models (SLMs) for automatic question generation as a complement to the prevalent use of their large counterparts in learning analytics research. We present a novel question generation pipeline that leverages both the text generation and the probabilistic reasoning abilities of SLMs to generate high-quality questions. Adopting a "generate-then-validate" strategy, our pipeline first performs expansive generation to create an abundance of candidate questions and refine them through selective validation based on novel probabilistic reasoning. We conducted two evaluation studies, one with seven human experts and the other with a large language model (LLM), to assess the quality of the generated questions. Most judges (humans or LLMs) agreed that the generated questions had clear answers and generally aligned well with the intended learning objectives. Our findings suggest that an SLM can effectively generate high-quality questions when guided by a well-designed pipeline that leverages its strengths. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_10110 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Generate-Then-Validate: A Novel Question Generation Approach Using Small Language Models Wei, Yumou Stamper, John Carvalho, Paulo F. Computation and Language Human-Computer Interaction We explore the use of small language models (SLMs) for automatic question generation as a complement to the prevalent use of their large counterparts in learning analytics research. We present a novel question generation pipeline that leverages both the text generation and the probabilistic reasoning abilities of SLMs to generate high-quality questions. Adopting a "generate-then-validate" strategy, our pipeline first performs expansive generation to create an abundance of candidate questions and refine them through selective validation based on novel probabilistic reasoning. We conducted two evaluation studies, one with seven human experts and the other with a large language model (LLM), to assess the quality of the generated questions. Most judges (humans or LLMs) agreed that the generated questions had clear answers and generally aligned well with the intended learning objectives. Our findings suggest that an SLM can effectively generate high-quality questions when guided by a well-designed pipeline that leverages its strengths. |
| title | Generate-Then-Validate: A Novel Question Generation Approach Using Small Language Models |
| topic | Computation and Language Human-Computer Interaction |
| url | https://arxiv.org/abs/2512.10110 |