Abstract
"This paper presents our system for CCL25-Eval Task 10, addressing Fine-Grained Chinese Hate Speech Recognition (FGCHSR). We propose a novel SRAG-MAV framework that synergistically integrates task reformulation(TR), Self-Retrieval-Augmented Generation (SRAG), and Multi-Round Accumulative Voting (MAV). Our method reformulates the quadruplet extraction task into triplet extraction, uses dynamic retrieval from the training set to create contextual prompts,and applies multi-round inference with voting to improve output stability and performance. Our system, based on the Qwen2.5-7B model, achieves a Hard Score of 26.66, a Soft Score of 48.35,and an Average Score of 37.505 on the STATE ToxiCN dataset, significantly outperforming base-lines such as GPT-4o (Average Score 15.63) and fine-tuned Qwen2.5-7B (Average Score 35.365).The code is available at https://github.com/king-wang123/CCL25-SRAG-MAV."
- Anthology ID:
- 2025.ccl-2.47
- 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:
- 395–402
- Language:
- URL:
- https://aclanthology.org/2025.ccl-2.47/
- DOI:
- Bibkey:
- Cite (ACL):
- Jiahao Wang, Ramen Liu, Longhui Zhang, and Jing Li. 2025. System Report for CCL25-Eval Task 10: SRAG-MAV for Fine-Grained Chinese Hate Speech Recognition. In Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025), pages 395–402, Jinan, China. Chinese Information Processing Society of China.
- Cite (Informal):
- System Report for CCL25-Eval Task 10: SRAG-MAV for Fine-Grained Chinese Hate Speech Recognition (Wang et al., CCL 2025)
- Copy Citation:
- PDF:
- https://aclanthology.org/2025.ccl-2.47.pdf