{
  "annotation_id": "04eceb95-fb8c-4409-985d-d684bb297e55",
  "date_created": "2026-02-17T05:53:20.113000Z",
  "date_modified": "2026-02-17T05:53:20.113000Z",
  "file_hash": "0502a207539d5cf9527dd2b8c719714299270792e697a036c6171275c796fee7",
  "private": false,
  "record": {
    "abstract": "This work proposes a contextualised detection framework for implicitly hateful speech, implemented as a multi-agent system comprising a central Moderator Agent and dynamically constructed Community Agents representing specific demographic groups. Our approach explicitly integrates socio-cultural context from publicly available knowledge sources, enabling identity-aware moderation that surpasses state-of-the-art prompting methods (zero-shot prompting, few-shot prompting, chain-of-thought prompting) and alternative approaches on a challenging ToxiGen dataset. We enhance the technical rigour of performance evaluation by incorporating balanced accuracy as a central metric of classification fairness that accounts for the trade-off between true positive and true negative rates. We demonstrate that our community-driven consultative framework significantly improves both classification accuracy and fairness across all target groups.",
    "arxiv_id": "2601.09342",
    "authors": [
      "Ewelina Gajewska",
      "Katarzyna Budzynska",
      "Jaros\u0142aw A Chudziak"
    ],
    "categories": [
      "cs.CL",
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "Improving Implicit Hate Speech Detection via a Community-Driven Multi-Agent Framework",
    "url": "https://arxiv.org/abs/2601.09342",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "7bb8d8eb-c473-401e-9036-08186163256d",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}