EUVIMEDEUVIMED entdecken
Crossref

Diffusion for Combating the Hallucination in Large Language Models (Student Abstract)

Hyojun Ahn, Joongheon Kim

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41119-41120

DOI: 10.1609/aaai.v40i48.42183 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Hyojun Ahn und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models (LLMs) often generate hallucinations—fluent yet factually incorrect responses—that undermine reliability in knowledge-intensive tasks. Existing approaches for hallucination mitigation typically rely on external retrieval modules or probability heuristics, which either require additional resources or lack interpretability. In this work, we propose a diffusion-based hallucination detection framework (DHDF) that leverages U-Net denoising to reconstruct consensus answers from multiple LLM outputs. If the diffusion process exhibits spurious convergence away from factual ground truth, it provides a clear signal of hallucination. To quantify factual correctness, we incorporate TruthfulQA scores as a fact-grounded evaluation metric, distinguishing well-aligned models (high scores) from hallucination-prone models (low scores). Experimental results demonstrate that convergence dynamics under diffusion, combined with fact-grounded QA evaluation, offer an effective and interpretable pathway for hallucination detection without relying on external knowledge bases.

Zitieren

APA

Ahn, H., & Kim, J. (2026). Diffusion for Combating the Hallucination in Large Language Models (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41119-41120. https://doi.org/10.1609/aaai.v40i48.42183

Vancouver

Ahn H, Kim J. Diffusion for Combating the Hallucination in Large Language Models (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41119-41120. doi:10.1609/aaai.v40i48.42183

BibTeX
@article{Ahn2026,
  author = {Ahn, Hyojun and Kim, Joongheon},
  title = {Diffusion for Combating the Hallucination in Large Language Models (Student Abstract)},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {48},
  pages = {41119--41120},
  doi = {10.1609/aaai.v40i48.42183}
}
Kostenlos starten →