Hallucinate Less by Thinking More: Aspect-Based Causal Abstention for Large Language Models

Vy Nguyen; Ziqi Xu; Jeffrey Chan; Estrid He; Feng Xia; Xiuzhen Zhang

AAAI 2026technical0 citations

Hallucinate Less by Thinking More: Aspect-Based Causal Abstention for Large Language Models

Vy Nguyen, Ziqi Xu, Jeffrey Chan, Estrid He, Feng Xia, Xiuzhen Zhang

Abstract

Large Language Models (LLMs) often produce fluent but factually incorrect responses, a phenomenon known as hallucination. Abstention, where the model chooses not to answer and instead outputs phrases such as "I don

BibTeX

@inproceedings{aaai2026_hallucinatelessb,
  title = {Hallucinate Less by Thinking More: Aspect-Based Causal Abstention for Large Language Models},
  author = {Vy Nguyen and Ziqi Xu and Jeffrey Chan and Estrid He and Feng Xia and Xiuzhen Zhang},
  booktitle = {AAAI 2026},
  year = {2026}
}