mlsanityData to 14 Oct 2026

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

arXiv 2506.00088 ↗First posted 30 May 2025cs.CL cs.AI cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 28 of its 46 references that are in the map. First posted on arXiv 30 May 2025.

Builds on

28 of 46 references.

References · 28

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  2. 2018Neural Ordinary Differential Equationscited by 3,779
  3. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  4. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  5. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  6. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  7. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,254
  8. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 767
  9. 2023The Internal State of an LLM Knows When It's Lyingcited by 659
  10. 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 506
  11. 2024INSIDE: LLMs' Internal States Retain the Power of Hallucination Detectioncited by 323
  12. 2020Scalable Gradients for Stochastic Differential Equationscited by 271
16 more
  1. 2024Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMscited by 259
  2. 2024LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinationscited by 244
  3. 2017Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equationscited by 203
  4. 2021Neural SDEs as Infinite-Dimensional GANscited by 161
  5. 2024Long-form factuality in large language modelscited by 155
  6. 2021Graph Neural Controlled Differential Equations for Traffic Forecastingcited by 133
  7. 2019Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of Viewcited by 113
  8. 2023Enhancing Uncertainty-Based Hallucination Detection with Stronger Focuscited by 99
  9. 2023Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblockscited by 78
  10. 2021Efficient and Accurate Gradients for Neural SDEscited by 71
  11. 2017Multi-level Residual Networks from Dynamical Systems Viewcited by 59
  12. 2021Neural Controlled Differential Equations for Online Prediction Taskscited by 46
  13. 2021Redesigning the Transformer Architecture with Insights from Multi-particle Dynamical Systemscited by 31
  14. 2021Attentive Neural Controlled Differential Equations for Time-series Classification and Forecastingcited by 29
  15. 2022ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generationcited by 27
  16. 2024PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamicscited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2026AgentHallu: Benchmarking Automated Hallucination Attribution of LLM-based Agentscited by 16
  2. 2026Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMscited by 14
  3. 2026MultiHaluDet: Multilingual Hallucination Detection via LLM Hidden State Probingcited by 5
  4. 2025When Bias Pretends to Be Truth: How Spurious Correlations Undermine Hallucination Detection in LLMscited by 3
  5. 2025Decoding Memories: An Efficient Pipeline for Self-Consistency Hallucination Detectioncited by 2
  6. 2026CausalGaze: Unveiling Hallucinations via Counterfactual Graph Intervention in Large Language Modelscited by 0