Abstract
"This paper presents the implementation approach we employ in the First Chinese Factivity Inference Evaluation 2025 (FIE2025). Factivity inference (FI) is a semantic understanding task related to judging the truth value of events, based on the use of semantic verbal elements, such as “believe”, “falsely claim”, “realize”. We approach factivity inference as a large language model(LLM) based task. We aim to enhance LLM’s discriminative capability by adequately integrating the task-specific information via prompts, as well as constructing dynamic few-shot datasets for fine-tuning. Additionally, we incorporate data augmentation and ensemble strategies to further boost the performance. Our approach achieves a score of 93.41% in the official evaluation of the shared task, ranking second in the leaderboard."
- Anthology ID:
- 2025.ccl-2.15
- Volume:
- Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025)
- Month:
- August
- Year:
- 2025
- Address:
- Jinan, China
- Editors:
- Hongfei Lin, Bin Li, Hongye Tan
- Venue:
- CCL
- SIG:
- Publisher:
- Chinese Information Processing Society of China
- Note:
- Pages:
- 128–133
- Language:
- URL:
- https://aclanthology.org/2025.ccl-2.15/
- DOI:
- Bibkey:
- Cite (ACL):
- Sunyan Gu, Taoyu Lu, Siqi Liu, Kan Guo, and Yan Shao. 2025. System Report for CCL25-Eval Task 4: Factivity Inference Based on Dynamic Few-Shot Learning. In Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025), pages 128–133, Jinan, China. Chinese Information Processing Society of China.
- Cite (Informal):
- System Report for CCL25-Eval Task 4: Factivity Inference Based on Dynamic Few-Shot Learning (Gu et al., CCL 2025)
- Copy Citation:
- PDF:
- https://aclanthology.org/2025.ccl-2.15.pdf