{
  "annotation_id": "3aa85d86-8ed6-4473-bb8d-26f810cb58d6",
  "date_created": "2026-02-17T05:53:20.509000Z",
  "date_modified": "2026-02-17T05:53:20.509000Z",
  "file_hash": "8a3f26f836f43c6551261afa9ba0f36e1aa712f2a5971df9089fa9e35fa00aaa",
  "private": false,
  "record": {
    "abstract": "Knowledge Graph Retrieval-Augmented Generation (KG-RAG) extends the RAG paradigm by incorporating structured knowledge from knowledge graphs, enabling Large Language Models (LLMs) to perform more precise and explainable reasoning. While KG-RAG improves factual accuracy in complex tasks, existing KG-RAG models are often severely overconfident, producing high-confidence predictions even when retrieved sub-graphs are incomplete or unreliable, which raises concerns for deployment in high-stakes domains. To address this issue, we propose Ca2KG, a Causality-aware Calibration framework for KG-RAG. Ca2KG integrates counterfactual prompting, which exposes retrieval-dependent uncertainties in knowledge quality and reasoning reliability, with a panel-based re-scoring mechanism that stabilises predictions across interventions. Extensive experiments on two complex QA datasets demonstrate that Ca2KG consistently improves calibration while maintaining or even enhancing predictive accuracy.",
    "arxiv_id": "2601.09241",
    "authors": [
      "Jing Ren",
      "Bowen Li",
      "Ziqi Xu",
      "Xinkun Zhang",
      "Haytham Fayek",
      "Xiaodong Li"
    ],
    "categories": [
      "cs.CL"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "title": "When to Trust: A Causality-Aware Calibration Framework for Accurate Knowledge Graph Retrieval-Augmented Generation",
    "url": "https://arxiv.org/abs/2601.09241",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "da8d1bca-2fca-4484-bebd-64ddaabc7d92",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}