AAAI 2026technical0 citations

Look Closer! An Adversarial Parametric Editing Framework for Hallucination Mitigation in VLMs

Jiayu Hu, Beibei Li, Jiangwei Xia, Yanjun Qin, Bing Ji, Zhongshi He

Abstract

While Vision-Language Models (VLMs) have garnered increasing attention in the AI community due to their promising practical applications, they exhibit persistent hallucination issues, generating outputs misaligned with visual inputs. Recent studies attribute these hallucinations to VLMs

BibTeX
@inproceedings{aaai2026_lookcloseranadve,
  title = {Look Closer! An Adversarial Parametric Editing Framework for Hallucination Mitigation in VLMs},
  author = {Jiayu Hu and Beibei Li and Jiangwei Xia and Yanjun Qin and Bing Ji and Zhongshi He},
  booktitle = {AAAI 2026},
  year = {2026}
}
Look Closer! An Adversarial Parametric Editing Framework for Hallucination Mitigation in VLMs · AAAI 2026