# System Report for CCL25-Eval Task 10: SRAG-MAV for Fine-Grained Chinese Hate Speech Recognition

arXiv: https://arxiv.org/abs/2507.18580 · HTML: https://mlsanity.com/paper/2507.18580/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 22 references that are in the map.
- First posted on arXiv 24 Jul 2025.

## Builds on (most cited first, 16 of 16)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [Exploring Hate Speech Detection in Multimodal Publications](https://mlsanity.com/paper/1910.03814/) (2019)
- [Toxicity Detection: Does Context Really Matter?](https://mlsanity.com/paper/2006.00998/) (2020)
- [Towards generalisable hate speech detection: a review on obstacles and solutions](https://mlsanity.com/paper/2102.08886/) (2021)
- [Large-Scale Hate Speech Detection with Cross-Domain Transfer](https://mlsanity.com/paper/2203.01111/) (2022)
- [Detecting Hate Speech in Multi-modal Memes](https://mlsanity.com/paper/2012.14891/) (2020)
- [Parallel Scaling Law for Language Models](https://mlsanity.com/paper/2505.10475/) (2025)
- [A Two-Stage Adaptation of Large Language Models for Text Ranking](https://mlsanity.com/paper/2311.16720/) (2023)
- [A Novel Global Feature-Oriented Relational Triple Extraction Model based on Table Filling](https://mlsanity.com/paper/2109.06705/) (2021)
- [STATE ToxiCN: A Benchmark for Span-level Target-Aware Toxicity Extraction in Chinese Hate Speech Detection](https://mlsanity.com/paper/2501.15451/) (2025)

## Built on by (most cited first, 3 of 3)

- [Retrieval-Augmented Multi-Prompt Ensemble for Minor-Grain Breeding Information Extraction](https://mlsanity.com/paper/2609.07134/) (2026)
- [UO-FIE: Combining Exact-Label Supervision with Graded Utility for Factivity Inference](https://mlsanity.com/paper/2609.28605/) (2026)
- [Route-Verify-Vote: Procedure-Conditioned Self-Consistency for Mixed-Domain Reasoning](https://mlsanity.com/paper/2610.08814/) (2026)

## Abstract (arXiv)

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 baselines 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.