About
Jiahui Geng is Assistant Professor at Linköping University. His research centres on the safety, trustworthiness, and alignment of large language models, including jailbreak attacks and defences, hallucination detection, machine unlearning, and multimodal safety calibration. He has published at ACL, EMNLP, AAAI, ICCV, NeurIPS, and IJCAI, and serves as Area Chair for ACL ARR. Previously postdoc at MBZUAI (with Karray, Gurevych, and Nakov), PhD from University of Stavanger (Marie Curie CLARIFY), MSc from RWTH Aachen.