多视角推理框架提升双语仇恨言论结构化解析准确率
SPAR-Hate: Auditor-Guided Multi-Perspective Role Reasoning for Bilingual Hate Speech Parsing
- 从受害者、管理员、文化旁观者三视角提取证据支撑的候选答案
- 在跨目标和文化隐喻场景下，联合指标提升12.3%（绝对）
- 适合需要高精度仇恨言论结构分析的研究与安全应用
仇恨言论研究已从粗粒度分类转向结构化解析，要求系统共同识别目标、支持论据及目标级标签。包含多个目标、局部解读冲突或文化编码语言的文本使关联关系难以恢复。SPAR-Hate 是一种审计员引导的多视角角色推理框架，用于双语仇恨言论解析。它将每篇文档分解为局部关注单元，从受害者、管理员和文化旁观者视角提取基于证据的候选项，在证据一致性和模式约束下解决候选冲突，并重构样本级预测。在 STATE-ToxiCN 和受控的 TBO 分割数据集上的实验显示，该方法在局部与 API 后端上均取得提升，尤其在严格联合目标-论据-标签指标上表现突出。全测试集成提示控制、组件消融与有限仲裁诊断揭示了分视角生成与仲裁机制的关键贡献。结构化教师轨迹也支持训练更小的学生模型。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。