HalluZig: Hallucination Detection using Zigzag Persistence

• URL: http://arxiv.org/abs/2601.01552v1
• Date: Sun, 04 Jan 2026 14:55:43 GMT
• Title: HalluZig: Hallucination Detection using Zigzag Persistence
• Authors: Shreyas N. Samaga, Gilberto Gonzalez Arroyo, Tamal K. Dey,
• Abstract summary: We introduce a new paradigm for hallucination detection by analyzing the dynamic topology of model's layer-wise attention.<n>Our core hypothesis is that factual and hallucinated generations exhibit distinct topological signatures.<n>We validate our framework, HalluZig, on multiple benchmarks, demonstrating that it outperforms strong baselines.
• Score: 0.1687274452793636
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The factual reliability of Large Language Models (LLMs) remains a critical barrier to their adoption in high-stakes domains due to their propensity to hallucinate. Current detection methods often rely on surface-level signals from the model's output, overlooking the failures that occur within the model's internal reasoning process. In this paper, we introduce a new paradigm for hallucination detection by analyzing the dynamic topology of the evolution of model's layer-wise attention. We model the sequence of attention matrices as a zigzag graph filtration and use zigzag persistence, a tool from Topological Data Analysis, to extract a topological signature. Our core hypothesis is that factual and hallucinated generations exhibit distinct topological signatures. We validate our framework, HalluZig, on multiple benchmarks, demonstrating that it outperforms strong baselines. Furthermore, our analysis reveals that these topological signatures are generalizable across different models and hallucination detection is possible only using structural signatures from partial network depth.

Related papers

• SIGMA: Scalable Spectral Insights for LLM Collapse [51.863164847253366]
  We introduce SIGMA (Spectral Inequalities for Gram Matrix Analysis), a unified framework for model collapse.<n>By utilizing benchmarks that deriving and deterministic bounds on the matrix's spectrum, SIGMA provides a mathematically grounded metric to track the contraction of the representation space.<n>We demonstrate that SIGMA effectively captures the transition towards states, offering both theoretical insights into the mechanics of collapse.
  arXiv  Detail & Related papers  (2026-01-06T19:47:11Z)
• CoPHo: Classifier-guided Conditional Topology Generation with Persistent Homology [14.522233245543687]
  Topology structure underpins research on performance and robustness.<n>Generation of synthetic graphs with desired properties for testing or release.<n>We propose Persistent Topology Generation with Conditional Homology (CoPHo)<n>Experiments on four generic/network datasets demonstrate that CoPHo outperforms existing methods at matching target metrics.
  arXiv  Detail & Related papers  (2025-12-17T13:10:22Z)
• A Graph Signal Processing Framework for Hallucination Detection in Large Language Models [0.0]
  We show that factual statements exhibit consistent "energy mountain" behavior with low-frequency convergence, while different hallucination types show distinct signatures.<n>A simple detector using spectral signatures achieves 88.75% accuracy versus 75% for perplexity-based baselines.<n>These findings indicate that spectral geometry may capture reasoning patterns and error behaviors, potentially offering a framework for detection in large language models.
  arXiv  Detail & Related papers  (2025-10-21T22:35:48Z)
• The Shape of Adversarial Influence: Characterizing LLM Latent Spaces with Persistent Homology [4.280045926995889]
  This study focuses on how adversarial inputs systematically affect the internal representation spaces of Large Language Models.<n>By quantifying the shape of activations and neuronal information flow, our architecture-agnostic framework reveals fundamental invariants of representational change.
  arXiv  Detail & Related papers  (2025-05-26T18:31:49Z)
• Rethinking Contrastive Learning in Graph Anomaly Detection: A Clean-View Perspective [54.605073936695575]
  Graph anomaly detection aims to identify unusual patterns in graph-based data, with wide applications in fields such as web security and financial fraud detection.<n>Existing methods rely on contrastive learning, assuming that a lower similarity between a node and its local subgraph indicates abnormality.<n>The presence of interfering edges invalidates this assumption, since it introduces disruptive noise that compromises the contrastive learning process.<n>We propose a Clean-View Enhanced Graph Anomaly Detection framework (CVGAD), which includes a multi-scale anomaly awareness module to identify key sources of interference in the contrastive learning process.
  arXiv  Detail & Related papers  (2025-05-23T15:05:56Z)
• Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models [70.03122709795122]
  Previous backdoor detection methods primarily focus on the static features of backdoor samples.<n>This study introduces a novel backdoor detection perspective named Dynamic Attention Analysis (DAA), showing that these dynamic characteristics serve as better indicators for backdoor detection.<n>Our approach significantly surpasses existing detection methods, achieving an average F1 Score of 79.49% and an AUC of 87.67%.
  arXiv  Detail & Related papers  (2025-04-29T07:59:35Z)
• Hallucination Detection in LLMs with Topological Divergence on Attention Graphs [60.83579255387347]
  Hallucination, i.e., generating factually incorrect content, remains a critical challenge for large language models.<n>We introduce TOHA, a TOpology-based HAllucination detector in the RAG setting.
  arXiv  Detail & Related papers  (2025-04-14T10:06:27Z)
• ChiroDiff: Modelling chirographic data with Diffusion Models [132.5223191478268]
  We introduce a powerful model-class namely "Denoising Diffusion Probabilistic Models" or DDPMs for chirographic data. Our model named "ChiroDiff", being non-autoregressive, learns to capture holistic concepts and therefore remains resilient to higher temporal sampling rate.
  arXiv  Detail & Related papers  (2023-04-07T15:17:48Z)
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
  We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
  arXiv  Detail & Related papers  (2022-06-23T14:16:30Z)
• A Probabilistic Generative Model for Typographical Analysis of Early Modern Printing [44.62884731273421]
  We propose a deep and interpretable probabilistic generative model to analyze glyph shapes in printed Early Modern documents. Our approach introduces a neural editor model that first generates well-understood printing perturbations from template parameters via interpertable latent variables. We show that our approach outperforms rigid interpretable clustering baselines (Ocular) and overly-flexible deep generative models (VAE) alike on the task of completely unsupervised discovery of typefaces in mixed-font documents.
  arXiv  Detail & Related papers  (2020-05-04T17:01:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.