{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,17]],"date-time":"2026-11-17T12:17:27Z","timestamp":1794917847732,"version":"4.9.1"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:p>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\u2011calibration 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.<\/jats:p>","DOI":"10.24963\/ijcai.2026\/77","type":"proceedings-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T22:01:13Z","timestamp":1789596073000},"page":"679-687","source":"Crossref","is-referenced-by-count":2,"title":["Double-Calibration: Towards Reliable LLMs via Calibrating Knowledge and Reasoning Confidence"],"prefix":"10.24963","author":[{"given":"Yuyin","family":"Lu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziran","family":"Liang","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanghui","family":"Rao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenqi","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fu Lee","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Science and Technology, Hong Kong Metropolitan University, Hong Kong SAR"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10584","event":{"name":"Thirty-Fifth International Joint Conference on Artificial Intelligence {IJCAI-26}","theme":"Artificial Intelligence","location":"Bremen, Germany","acronym":"IJCAI-2026","number":"35","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2026,8,15]]},"end":{"date-parts":[[2026,8,21]]}},"container-title":["Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2026,11,17]],"date-time":"2026-11-17T11:27:42Z","timestamp":1794914862000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2026\/77"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2026\/77","relation":{},"subject":[],"published":{"date-parts":[[2026,9]]}}}