StateCloud at Critical Questions Generation: Prompt Engineering for Critical Question Generation
This paper presents StateCloud's submission to the Critical Questions Generation (CQs-Gen) shared task at the Argument Mining Workshop 2025.To generate high-quality critical questions from argumentative texts, we propose a framework that combines prompt engineering with few-shot learning to effectively guide generative models.Additionally, we ensemble outputs from diverse large language models (LLMs) to enhance accuracy.Notably, our approach achieved 3rd place in the competition, demonstrating the viability of prompt engineering strategies for argumentative tasks.
Authors
- J.-G. Zhang
- Binghuai Lin
- Dongming Yang (ORCID: https://orcid.org/0000-0002-1478-9642)
Institutions
- China Telecom (China) (CN)
- Cloud Computing Center (CN)
Publication Details
- Published
- 2025-01-01
- DOI
- https://doi.org/10.18653/v1/2025.argmining-1.24
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 0.00