{"slug": "spar-hate-an-auditor-guided-multi-agent-framework-for-bilingual-hate-speech", "title": "SPAR-Hate: An Auditor-Guided Multi-Agent Framework for Bilingual Hate Speech Parsing", "summary": "Researchers propose SPAR-Hate, an auditor-guided multi-agent framework for bilingual hate speech parsing that decomposes documents into clause-level units and generates evidence-grounded judgments from Victim, Moderator, and Cultural Bystander perspectives. On the STATE-ToxiCN and TBO benchmarks, SPAR-Hate achieves state-of-the-art results in bilingual multi-tuple extraction, with the largest gains under stricter structural evaluation metrics.", "body_md": "arXiv:2608.22018v1 Announce Type: new\nAbstract: Hate speech detection has recently shifted from coarse-grained classification to structured parsing, where systems must jointly identify hateful targets, arguments, and target-level labels. However, existing studies primarily emphasize benchmark evaluation while paying less attention to the cultural, linguistic, and social-group challenges involved in structured hate speech parsing. To address these challenges, we propose SPAR-Hate, an auditor-guided multi-agent framework for bilingual hate speech parsing. The framework first decomposes documents into clause-level decision units and then generates evidence-grounded judgments from three complementary perspectives: Victim, Moderator, and Cultural Bystander. An evidence-constrained arbitration process resolves conflicts among role-specific predictions and aggregates them into structured sample-level outputs. Experiments on the STATE-ToxiCN and TBO benchmarks show that SPAR-Hate consistently improves bilingual hate parsing across diverse large language models. The framework achieves state-of-the-art results on bilingual multi-tuple extraction tasks, with the largest gains observed under stricter structural evaluation metrics.", "url": "https://wpnews.pro/news/spar-hate-an-auditor-guided-multi-agent-framework-for-bilingual-hate-speech", "canonical_source": "https://www.machinebrief.com/news/spar-hate-an-auditor-guided-multi-agent-framework-for-biling-21fh", "published_at": "2026-08-25 04:00:00+00:00", "updated_at": "2026-08-25 05:14:23.580059+00:00", "lang": "en", "topics": ["artificial-intelligence", "natural-language-processing", "ai-agents"], "entities": ["SPAR-Hate", "STATE-ToxiCN", "TBO"], "alternates": {"html": "https://wpnews.pro/news/spar-hate-an-auditor-guided-multi-agent-framework-for-bilingual-hate-speech", "markdown": "https://wpnews.pro/news/spar-hate-an-auditor-guided-multi-agent-framework-for-bilingual-hate-speech.md", "text": "https://wpnews.pro/news/spar-hate-an-auditor-guided-multi-agent-framework-for-bilingual-hate-speech.txt", "jsonld": "https://wpnews.pro/news/spar-hate-an-auditor-guided-multi-agent-framework-for-bilingual-hate-speech.jsonld"}}