ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2506.00088
9
0

HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs

30 May 2025
Qing Li
Jiahui Geng
Zongxiong Chen
Derui Zhu
Yuxia Wang
Congbo Ma
Chenyang Lyu
Fakhri Karray
ArXiv (abs)PDFHTML
Main:8 Pages
7 Figures
Bibliography:5 Pages
4 Tables
Appendix:1 Pages
Abstract

In recent years, large language models (LLMs) have made remarkable advancements, yet hallucination, where models produce inaccurate or non-factual statements, remains a significant challenge for real-world deployment. Although current classification-based methods, such as SAPLMA, are highly efficient in mitigating hallucinations, they struggle when non-factual information arises in the early or mid-sequence of outputs, reducing their reliability. To address these issues, we propose Hallucination Detection-Neural Differential Equations (HD-NDEs), a novel method that systematically assesses the truthfulness of statements by capturing the full dynamics of LLMs within their latent space. Our approaches apply neural differential equations (Neural DEs) to model the dynamic system in the latent space of LLMs. Then, the sequence in the latent space is mapped to the classification space for truth assessment. The extensive experiments across five datasets and six widely used LLMs demonstrate the effectiveness of HD-NDEs, especially, achieving over 14% improvement in AUC-ROC on the True-False dataset compared to state-of-the-art techniques.

View on arXiv
@article{li2025_2506.00088,
  title={ HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs },
  author={ Qing Li and Jiahui Geng and Zongxiong Chen and Derui Zhu and Yuxia Wang and Congbo Ma and Chenyang Lyu and Fakhri Karray },
  journal={arXiv preprint arXiv:2506.00088},
  year={ 2025 }
}
Comments on this paper