What do Geometric Hallucination Detection Metrics Actually Measure?

• URL: http://arxiv.org/abs/2602.09158v1
• Date: Mon, 09 Feb 2026 20:04:49 GMT
• Title: What do Geometric Hallucination Detection Metrics Actually Measure?
• Abstract summary: Hallucination remains a barrier to deploying generative models in high-consequence applications.<n>We show that different geometric statistics capture different types of hallucinations.<n>We introduce a simple normalization method to mitigate the effect of domain shift on geometric statistics.
• Score: 8.084840813224597
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Hallucination remains a barrier to deploying generative models in high-consequence applications. This is especially true in cases where external ground truth is not readily available to validate model outputs. This situation has motivated the study of geometric signals in the internal state of an LLM that are predictive of hallucination and require limited external knowledge. Given that there are a range of factors that can lead model output to be called a hallucination (e.g., irrelevance vs incoherence), in this paper we ask what specific properties of a hallucination these geometric statistics actually capture. To assess this, we generate a synthetic dataset which varies distinct properties of output associated with hallucination. This includes output correctness, confidence, relevance, coherence, and completeness. We find that different geometric statistics capture different types of hallucinations. Along the way we show that many existing geometric detection methods have substantial sensitivity to shifts in task domain (e.g., math questions vs. history questions). Motivated by this, we introduce a simple normalization method to mitigate the effect of domain shift on geometric statistics, leading to AUROC gains of +34 points in multi-domain settings.

Related papers

• Beyond Language Priors: Diagnosing and Fixing Visual-Origin Hallucinations in Multimodal LLM [37.0916688511164]
  We present evidence for visual-origin hallucination, where hallucinations arise from incorrect visual feature extraction and misalignment between image and text embeddings.<n>We propose Adversarial Contrastive Fine-Tuning (ACFT) to correct this problem.<n>ACFT achieves state-of-the-art performance on POPE, MME, and four description-level hallucination benchmarks across LLaVA, MiniGPT-4, and Qwen2.5-VL.
  arXiv  Detail & Related papers  (2026-08-31T18:38:24Z)
• Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models [62.932580559941414]
  Vision-Language Models (VLMs) frequently "hallucinate" - generate plausible yet factually incorrect statements.<n>We propose a new paradigm for diagnosing hallucinations, recasting them from static output errors into dynamic pathologies of a model's computational cognition.
  arXiv  Detail & Related papers  (2026-03-16T17:20:38Z)
• HACK: Hallucinations Along Certainty and Knowledge Axes [66.66625343090743]
  We propose a framework for categorizing hallucinations along two axes: knowledge and certainty.<n>We identify a particularly concerning subset of hallucinations where models hallucinate with certainty despite having the correct knowledge internally.
  arXiv  Detail & Related papers  (2025-10-28T09:34:31Z)
• Counting Hallucinations in Diffusion Models [34.45858211220468]
  Diffusion probabilistic models (DPMs) have demonstrated remarkable progress in generative tasks, such as image and video synthesis.<n>They often produce hallucinated samples (hallucinations) that conflict with real-world knowledge.<n>Despite their prevalence, the lack of feasible methodologies for systematically quantifying such hallucinations hinders progress.
  arXiv  Detail & Related papers  (2025-10-15T01:48:04Z)
• Mitigating Diffusion Model Hallucinations with Dynamic Guidance [75.90458880492054]
  Diffusion models often produce hallucinatory samples with structural inconsistencies that lie outside of the support of the true data distribution.<n>We introduce Dynamic Guidance, which mitigates hallucinations by selectively sharpening the score function only along the pre-determined directions known to cause artifacts.<n>To our knowledge, this is the first approach that addresses hallucinations at generation time rather than through post-hoc filtering.
  arXiv  Detail & Related papers  (2025-10-06T20:31:13Z)
• Theoretical Foundations and Mitigation of Hallucination in Large Language Models [0.0]
  Hallucination in Large Language Models (LLMs) refers to the generation of content that is not faithful to the input or the real-world facts.<n>This paper provides a rigorous treatment of hallucination in LLMs, including formal definitions and theoretical analyses.
  arXiv  Detail & Related papers  (2025-07-20T15:22:34Z)
• Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations [82.42811602081692]
  This paper introduces a subsequence association framework to systematically trace and understand hallucinations.<n>Key insight is hallucinations that arise when dominant hallucinatory associations outweigh faithful ones.<n>We propose a tracing algorithm that identifies causal subsequences by analyzing hallucination probabilities across randomized input contexts.
  arXiv  Detail & Related papers  (2025-04-17T06:34:45Z)
• Hallucination Detection: A Probabilistic Framework Using Embeddings Distance Analysis [2.089191490381739]
  We introduce a mathematically sound methodology to reason about hallucination, and leverage it to build a tool to detect hallucinations.<n>To the best of our knowledge, we are the first to show that hallucinated content has structural differences with respect to correct content.<n>We leverage these structural differences to develop a tool to detect hallucinated responses, achieving an accuracy of 66% for a specific configuration of system parameters.
  arXiv  Detail & Related papers  (2025-02-10T09:44:13Z)
• Distinguishing Ignorance from Error in LLM Hallucinations [43.62904897907926]
  We distinguish between two types of hallucinations: ones where the model does not hold the correct answer in its parameters, which we term HK-, and ones where the model answers incorrectly despite having the required knowledge, termed HK+.<n>We show that different models hallucinate on different examples, which motivates constructing model-specific hallucination datasets for training detectors.
  arXiv  Detail & Related papers  (2024-10-29T14:31:33Z)
• Understanding Hallucinations in Diffusion Models through Mode Interpolation [89.10226585746848]
  We study a particular failure mode in diffusion models, which we term mode mode. We find that diffusion models smoothly "interpolate" between nearby data modes in the training set, to generate samples that are completely outside the support of the original training distribution. We show how hallucination leads to the generation of combinations of shapes that never existed.
  arXiv  Detail & Related papers  (2024-06-13T17:43:41Z)
• On Large Language Models' Hallucination with Regard to Known Facts [74.96789694959894]
  Large language models are successful in answering factoid questions but are also prone to hallucination. We investigate the phenomenon of LLMs possessing correct answer knowledge yet still hallucinating from the perspective of inference dynamics. Our study shed light on understanding the reasons for LLMs' hallucinations on their known facts, and more importantly, on accurately predicting when they are hallucinating.
  arXiv  Detail & Related papers  (2024-03-29T06:48:30Z)
• AutoHall: Automated Hallucination Dataset Generation for Large Language Models [56.92068213969036]
  This paper introduces a method for automatically constructing model-specific hallucination datasets based on existing fact-checking datasets called AutoHall. We also propose a zero-resource and black-box hallucination detection method based on self-contradiction.
  arXiv  Detail & Related papers  (2023-09-30T05:20:02Z)

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.