mlsanityData to 7 Oct 2026

SPAR-Hate: Auditor-Guided Multi-Perspective Role Reasoning for Bilingual Hate Speech Parsing

arXiv 2608.22018 ↗First posted 22 Aug 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 37 references that are in the map. First posted on arXiv 22 Aug 2026.

Builds on

17 of 37 references.

References · 17

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  3. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  4. 2026DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligencecited by 877
  5. 2017Automated Hate Speech Detection and the Problem of Offensive Languagecited by 724
  6. 2023Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizescited by 710
  7. 2022ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detectioncited by 419
  8. 2020HateXplain: A Benchmark Dataset for Explainable Hate Speech Detectioncited by 403
  9. 2019Social Bias Frames: Reasoning about Social and Power Implications of Languagecited by 377
  10. 2021Latent Hatred: A Benchmark for Understanding Implicit Hate Speechcited by 216
  11. 2020HateCheck: Functional Tests for Hate Speech Detection Modelscited by 215
  12. 2022Distilling Reasoning Capabilities into Smaller Language Modelscited by 155
5 more
  1. 2019Multilingual and Multi-Aspect Hate Speech Analysiscited by 133
  2. 2023Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarkscited by 45
  3. 2023HARE: Explainable Hate Speech Detection with Step-by-Step Reasoningcited by 30
  4. 2024ToxiCloakCN: Evaluating Robustness of Offensive Language Detection in Chinese with Cloaking Perturbationscited by 30
  5. 2025STATE ToxiCN: A Benchmark for Span-level Target-Aware Toxicity Extraction in Chinese Hate Speech Detectioncited by 9

Built on by

Not cited yet.