Lune

ACL2025Top-tier venue

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

Qing Li, Jiahui Geng, Zongxiong Chen, Derui Zhu, Yuxia Wang, Congbo Ma, Chenyang Lyu, Fakhri Karray

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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models cites DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. DOUBT: Decoupled Object-level Understanding and Bridging via vMF-based Trustworthiness for Hallucination Detection in MLLMsKaiqi Chen, Yang Qin, Changhao He, Xi Peng et al.ICML 2026

Builds on20

  1. TruthfulQA: Measuring How Models Mimic Human FalsehoodsStephanie Lin, Jacob Hilton, Owain EvansACL 2022 · 3,228 citations
  2. Neural Controlled Differential Equations for Irregular Time SeriesPatrick Kidger, James Morrill, James Foster, Terry J. LyonsNeurIPS 2020 · 850 citations
  3. Graph Neural Controlled Differential Equations for Traffic ForecastingJeongwhan Choi, Hwangyong Choi, Jeehyun Hwang, Noseong ParkAAAI 2022 · 441 citations
  4. DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding SharingPengcheng He, Jianfeng Gao, Weizhu ChenICLR 2023 · 394 citations
  5. SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language ModelsPotsawee Manakul, Adian Liusie, Mark J. F. GalesEMNLP 2023 · 331 citations

Related papers

  1. The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language ModelsJunyi Li, Jie Chen, Ruiyang Ren, Xiaoxue Cheng et al.ACL 2024 · 49 citations
  2. InterrogateLLM: Zero-Resource Hallucination Detection in LLM-Generated AnswersYakir Yehuda, Itzik Malkiel, Oren Barkan, Jonathan Weill et al.ACL 2024
  3. HyperEdit: Mitigating Hallucinations of Large Language Models via Hyperbolic Representation EditingTongxu Lin, Junping Du, Zhe Xue, Meiyu Liang et al.KDD 2026
  4. HARP: Hallucination Detection via Reasoning Subspace ProjectionJunjie Hu, Gang Tu, Shengyu Cheng, Jinxin Li et al.ICLR 2026 · 6 citations
  5. HaDeMiF: Hallucination Detection and Mitigation in Large Language ModelsXiaoling Zhou, Mingjie Zhang, Zhemg Lee, Wei Ye et al.ICLR 2025
Dusk over the sea between two cliffs drawn in fine vertical lines