{
  "annotation_id": "e9cfc338-778e-4d59-af60-ea2e6215ba51",
  "date_created": "2026-02-17T05:53:24.272000Z",
  "date_modified": "2026-02-17T05:53:24.272000Z",
  "file_hash": "30cc41c392c9da047802121fe4d1497336373c577fb61977773b06d2a7d1372e",
  "private": false,
  "record": {
    "abstract": "Large Language Models (LLMs) and Large Reasoning Models (LRMs) offer transformative potential for high-stakes domains like finance and law, but their tendency to hallucinate, generating factually incorrect or unsupported content, poses a critical reliability risk. This paper introduces a comprehensive operational framework for hallucination management, built on a continuous improvement cycle driven by root cause awareness. We categorize hallucination sources into model, data, and context-related factors, allowing targeted interventions over generic fixes. The framework integrates multi-faceted detection methods (e.g., uncertainty estimation, reasoning consistency) with stratified mitigation strategies (e.g., knowledge grounding, confidence calibration). We demonstrate its application through a tiered architecture and a financial data extraction case study, where model, context, and data tiers form a closed feedback loop for progressive reliability enhancement. This approach provides a systematic, scalable methodology for building trustworthy generative AI systems in regulated environments.",
    "arxiv_id": "2601.09929",
    "authors": [
      "Ahmad Pesaranghader",
      "Erin Li"
    ],
    "categories": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "title": "Hallucination Detection and Mitigation in Large Language Models",
    "url": "https://arxiv.org/abs/2601.09929",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "8fe3d3ee-2f54-43cf-9efa-c51db1397c08",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}