mlsanityData to 13 Oct 2026

TDGNet: Hallucination Detection in Diffusion Language Models via Temporal Dynamic Graphs

arXiv 2602.08048 ↗First posted 8 Feb 2026cs.CLcited by 8

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Diffusion language models (D-LLMs) offer parallel denoising and bidirectional context, but hallucination detection for D-LLMs remains underexplored. Prior detectors developed for auto-regressive LLMs typically rely on single-pass cues and do not directly transfer to diffusion generation, where factuality evidence is distributed across the denoising trajectory and may appear, drift, or be self-corrected over time. We introduce TDGNet, a temporal dynamic graph framework that formulates hallucination detection as learning over evolving token-level attention graphs. At each denoising step, we sparsify the attention graph and update per-token memories via message passing, then apply temporal attention to aggregate trajectory-wide evidence for final prediction. Experiments on LLaDA-8B and Dream-7B across QA benchmarks show consistent AUROC improvements over output-based, latent-based, and static-graph baselines, with single-pass inference and modest overhead. These results highlight the importance of temporal reasoning on attention graphs for robust hallucination detection in diffusion language models.

Key facts. Cited by 8 papers in the map (data through 13 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 46 of its 51 references that are in the map. First posted on arXiv 8 Feb 2026.

Builds on

46 of 51 references.

References · 46

  1. 2017Attention Is All You Needcited by 60,106
  2. 2020Language Models are Few-Shot Learnerscited by 32,320
  3. 2023GPT-4 Technical Reportcited by 18,278
  4. 2022Training language models to follow instructions with human feedbackcited by 15,856
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,072
  6. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,318
  7. 2017Graph Attention Networkscited by 8,888
  8. 2017Inductive Representation Learning on Large Graphscited by 6,303
  9. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,539
  10. 2018How Powerful are Graph Neural Networks?cited by 4,373
  11. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,716
  12. 2017Neural Message Passing for Quantum Chemistrycited by 3,471
34 more
  1. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,925
  2. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,805
  3. 2018Relational inductive biases, deep learning, and graph networkscited by 1,353
  4. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,268
  5. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,012
  6. 2025Large Language Diffusion Modelscited by 888
  7. 2024Simple and Effective Masked Diffusion Language Modelscited by 816
  8. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 810
  9. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 798
  10. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 750
  11. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distributioncited by 725
  12. 2023The Internal State of an LLM Knows When It's Lyingcited by 652
  13. 2025Dream 7B: Diffusion Large Language Modelscited by 528
  14. 2020Temporal Graph Networks for Deep Learning on Dynamic Graphscited by 525
  15. 2020Inductive Representation Learning on Temporal Graphscited by 457
  16. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 445
  17. 2019Predicting Dynamic Embedding Trajectory in Temporal Interaction Networkscited by 445
  18. 2024INSIDE: LLMs' Internal States Retain the Power of Hallucination Detectioncited by 321
  19. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 289
  20. 2024Scaling Diffusion Language Models via Adaptation from Autoregressive Modelscited by 271
  21. 2024Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMscited by 255
  22. 2024LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinationscited by 236
  23. 2023A Reparameterized Discrete Diffusion Model for Text Generationcited by 152
  24. 2024Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Mapscited by 141
  25. 2024HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detectioncited by 97
  26. 2024Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Modelscited by 86
  27. 2022Mix and Match: Learning-free Controllable Text Generation using Energy Language Modelscited by 66
  28. 2025Steer LLM Latents for Hallucination Detectioncited by 50
  29. 2025Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Modelscited by 33
  30. 2025A Survey on Parallel Text Generation: From Parallel Decoding to Diffusion Language Modelscited by 30
  31. 2024Mitigating Entity-Level Hallucination in Large Language Modelscited by 17
  32. 2025Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Modelscited by 16
  33. 2024FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guaranteescited by 6
  34. 2025Neural Message-Passing on Attention Graphs for Hallucination Detectioncited by 5

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2026: 8.

8 papers.

  1. 2026Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Modelscited by 3
  2. 2026Measuring Temporal Linguistic Emergence in Diffusion Language Modelscited by 1
  3. 2026HIVE: Hidden-Evidence Verification for Hallucination Detection in Diffusion Large Language Modelscited by 1
  4. 2026TRE: Training-Free Hallucination Detection for Diffusion Language Modelscited by 0
  5. 2026DeMTS: Denoising Trajectories as Multivariate Time Series for Hallucination Detection in Diffusion Language Modelscited by 0
  6. 2026The Temporal Tug-of-War: Visualizing and Detecting RAG Conflicts in Diffusion Models via Trajectory Variancecited by 0
  7. 2026Before the Token Commits: Trajectory-Level Benchmarking of Visual Hallucinations in Diffusion VLMscited by 0
  8. 2026The Detectability Gap: Hidden Heterogeneity in Hallucination Detection Across Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Lost in Diffusion: Uncovering Hallucination Patterns and Failure Modes in Diffusion Large Language Models
  2. 2026HalluSAE: Detecting Hallucinations in Large Language Models via Sparse Auto-Encoders
  3. 2025Hallucination Detection and Mitigation with Diffusion in Multi-Variate Time-Series Foundation Models
  4. 2026AURORA: Asymmetry and Update-Induced Rotation for Robust Hallucination Detection in Large Language Models
  5. 2026Predictive Coding and Information Bottleneck for Hallucination Detection in Large Language Models
  6. 2026Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models
  7. 2026HalluZig: Hallucination Detection using Zigzag Persistence
  8. 2026External Observers May See More Clearly: Cross-Model Span-Level Hallucination Detection in Large Language Models via Hidden State Probing