SPAR-Hate: Auditor-Guided Multi-Perspective Role Reasoning for Bilingual Hate Speech Parsing
cs.AI
Submitted: 2026-08-22
Updated: 2026-10-14
Comments: 16 pages, 2 figures. Submitted to EMNLP 2026
License: http://creativecommons.org/licenses/by/4.0/
The gist: Hate speech research has moved from coarse-grained classification towards structured parsing, where systems jointly identify targets, supporting arguments, and target-level labels.
Abstract
Hate speech research has moved from coarse-grained classification towards structured parsing, where systems jointly identify targets, supporting arguments, and target-level labels. Documents with multiple targets, conflicting local readings, or culturally coded language make these bindings difficult to recover. SPAR-Hate is an auditor-guided multi-perspective role-reasoning framework for bilingual hate speech parsing. It decomposes each document into local focus units, elicits evidence-grounded candidates from Victim, Moderator, and Cultural Bystander perspectives, resolves candidate conflicts under grounding and schema constraints, and reassembles sample-level predictions. Experiments on STATE-ToxiCN and a controlled TBO split show gains across local and API backbones, concentrated on strict joint target-argument-label metrics. Full-test integrated-prompt controls, component ablations, and bounded-arbitration diagnostics identify the contribution of separated perspective generation and arbitration. Structured teacher traces also support training a smaller student model.
Sources
- QLoRA: Efficient Finetuning of Quantized LLMs
- Improving Factuality and Reasoning in Language Models through Multiagent Debate
- MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
- LoRA: Low-Rank Adaptation of Large Language Models
- Efficient Memory Management for Large Language Model Serving with PagedAttention
- Exploring the Capability Boundaries of LLMs in Mastering of Chinese Chouxiang Language
- Distilling Reasoning Capabilities into Smaller Language Models
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- Qwen3 Technical Report
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems