# From Triage to Impact: A Multi-Hop Reasoning Benchmark for Explainable Persian Hate Speech

arXiv: https://arxiv.org/abs/2610.20370 · HTML: https://mlsanity.com/paper/2610.20370/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 26 references that are in the map.
- First posted on arXiv 14 Oct 2026.

## Placed in

- LLM reasoning

## Builds on (most cited first, 6 of 6)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [ParsBERT: Transformer-based Model for Persian Language Understanding](https://mlsanity.com/paper/2005.12515/) (2020)
- [From Languages to Geographies: Towards Evaluating Cultural Bias in Hate Speech Datasets](https://mlsanity.com/paper/2404.17874/) (2024)
- [MFTCXplain: A Multilingual Benchmark Dataset for Evaluating the Moral Reasoning of LLMs through Multi-hop Hate Speech Explanation](https://mlsanity.com/paper/2506.19073/) (2025)
- [Culture Matters in Toxic Language Detection in Persian](https://mlsanity.com/paper/2506.03458/) (2025)

## Abstract (arXiv)

Hate speech has become increasingly prevalent on social media, raising concerns about its detection, interpretation, and moderation. Persian, a relatively low-resource language, lacks sufficient annotated data and computational resources for fine-grained hate speech analysis. In this study, we introduce a fine-grained, multi-hop benchmark for explainable Persian hate speech analysis, covering content triage, target identification, hate tactic and moral foundation analysis, textual evidence extraction, harmful narrative inference, and severity assessment. By evaluating state-of-the-art large language models (LLMs), we find that performance generally declines as tasks require more fine-grained semantic and inferential reasoning. Proprietary models generally outperform open-weight models, while reasoning-oriented models show no consistent advantage. Incorporating intermediate reasoning steps substantially improves severity prediction compared with one-shot assessment. Our analysis further reveals that Incitement to Violence or Harm is most strongly associated with higher severity, while political-affiliation targets are particularly associated with subversion-based moral framing. Overall, this work provides insights into LLM-based hate speech analysis and supports more accountable moderation of Persian-language social media. The benchmark is publicly available at https://github.com/kalhorghazal/From-Triage-to-Impact.