Proceedings

Double-Calibration: Towards Reliable LLMs via Calibrating Knowledge and Reasoning Confidence

Yuyin Lu, Ziran Liang, Yanghui Rao, Wenqi Fan, Fu Lee Wang, Qing Li

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 679-687.

https://doi.org/10.24963/ijcai.2026/77

Keywords

  • Knowledge Representation and Reasoning: Learning and reasoning
  • Knowledge Representation and Reasoning: Applications
  • AI Ethics, Trust, Fairnes: Trustworthy AI
  • Uncertainty in AI: Applications

Abstract

Reliable reasoning in Large Language Models (LLMs) is challenged by their propensity for hallucination. While augmenting LLMs with Knowledge Graphs (KGs) improves factual accuracy, existing KG-augmented methods fail to quantify epistemic uncertainty in both the retrieved evidence and LLMs' reasoning. To bridge this gap, we introduce DoublyCal, a framework built on a novel double‑calibration principle. DoublyCal employs a lightweight proxy model to first generate KG evidence alongside a calibrated evidence confidence. This calibrated supporting evidence then guides a black-box LLM, yielding final predictions that are not only more accurate but also well-calibrated, with confidence scores traceable to the uncertainty of the supporting evidence. Experiments on knowledge-intensive benchmarks show that DoublyCal significantly improves both the accuracy and confidence calibration of black-box LLMs while maintaining low token cost.

Yuyin Lu, Ziran Liang, Yanghui Rao, Wenqi Fan, Fu Lee Wang, and Qing Li. 2026. Double-Calibration: Towards Reliable LLMs via Calibrating Knowledge and Reasoning Confidence. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 679–687. https://doi.org/10.24963/ijcai.2026/77
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards