On Hallucinations in Inverse Problems: Fundamental Limits and Provable Assessment Methods

• URL: http://arxiv.org/abs/2605.13146v1
• Date: Wed, 13 May 2026 08:11:43 GMT
• Title: On Hallucinations in Inverse Problems: Fundamental Limits and Provable Assessment Methods
• Abstract summary: Deep neural networks can produce hallucinations, realistic-looking but incorrect details, undermining their reliability.<n>We develop a theoretical framework showing that such hallucinations are not merely artifacts of particular models, but can arise from the ill-posed nature of the inverse problem itself.
• Score: 1.953336755301616
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Artificial intelligence (AI) has transformed imaging inverse problems, from medical diagnostics to Earth observation. Yet deep neural networks can produce hallucinations, realistic-looking but incorrect details, undermining their reliability, especially when ground truth data is unavailable. We develop a theoretical framework showing that such hallucinations are not merely artifacts of particular models, but can arise from the ill-posed nature of the inverse problem itself. We derive necessary and sufficient conditions for hallucinations, together with computable bounds on their magnitude that depend only on the forward model. Building on this theory, we introduce algorithms to: (1) estimate the minimum hallucination magnitude achievable by any reconstruction model for a given input; (2) assess the faithfulness of reconstructed details by a given reconstruction model. Experiments across three imaging tasks demonstrate that our approach applies broadly, including to modern generative models, and provides a principled way to quantify and evaluate AI hallucinations.

Related papers

• 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)
• Triggering hallucinations in model-based MRI reconstruction via adversarial perturbations [3.325046116674658]
  hallucinations may endanger patient health as they can lead to incorrect diagnoses.<n>In this work, we aim to quantify the extent to which state-of-the-art generative models suffer from hallucinations in the context of magnetic resonance image reconstruction.<n>We perform this evaluation on the brain and knee images from the fastMRI data set using UNet and end-to-end VarNet architectures.
  arXiv  Detail & Related papers  (2026-02-20T11:55:22Z)
• CHEM: Estimating and Understanding Hallucinations in Deep Learning for Image Processing [17.573711532387176]
  U-Net and other U-shaped architectures have achieved significant success in image deconvolution tasks.<n>However, these methods might generate unrealistic artifacts or hallucinations, which can interfere with analysis in safety-critical scenarios.<n>This paper introduces a novel approach for quantifying and comprehending hallucination artifacts to ensure trustworthy computer vision models.
  arXiv  Detail & Related papers  (2025-12-10T16:20:00Z)
• Review of Hallucination Understanding in Large Language and Vision Models [65.29139004945712]
  We present a framework for characterizing both image and text hallucinations across diverse applications.<n>Our investigations reveal that hallucinations often stem from predictable patterns in data distributions and inherited biases.<n>This survey provides a foundation for developing more robust and effective solutions to hallucinations in real-world generative AI systems.
  arXiv  Detail & Related papers  (2025-09-26T09:23:08Z)
• How Large Language Models are Designed to Hallucinate [0.42970700836450487]
  We argue that hallucination is a structural outcome of the transformer architecture.<n>Our contribution is threefold: (1) a comparative account showing why existing explanations are insufficient; (2) a predictive taxonomy of hallucination linked to existential structures with proposed benchmarks; and (3) design directions toward "truth-constrained" architectures capable of withholding or deferring when disclosure is absent.
  arXiv  Detail & Related papers  (2025-09-19T16:46:27Z)
• MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM [58.2298313720146]
  Multimodal hallucinations are multi-sourced and arise from diverse causes.<n>Existing benchmarks fail to adequately distinguish between perception-induced hallucinations and reasoning-induced hallucinations.
  arXiv  Detail & Related papers  (2025-05-30T05:54:36Z)
• Mitigating Low-Level Visual Hallucinations Requires Self-Awareness: Database, Model and Training Strategy [53.07517728420411]
  We introduce the first instruction database specifically focused on hallucinations in low-level vision tasks.<n>We propose the Self-Awareness Failure Elimination (SAFEQA) model to improve the perception and comprehension abilities of the model in low-level vision tasks.<n>We conduct comprehensive experiments on low-level vision tasks, with the results demonstrating that our proposed method significantly enhances self-awareness of the model in these tasks and reduces hallucinations.
  arXiv  Detail & Related papers  (2025-03-26T16:05:01Z)
• The Law of Knowledge Overshadowing: Towards Understanding, Predicting, and Preventing LLM Hallucination [85.18584652829799]
  We introduce a novel framework to quantify factual hallucinations by modeling knowledge overshadowing.<n>We propose a new decoding strategy CoDa, to mitigate hallucinations, which notably enhance model factuality on Overshadow (27.9%), MemoTrap (13.1%) and NQ-Swap (18.3%)
  arXiv  Detail & Related papers  (2025-02-22T08:36:06Z)
• Towards a Systematic Evaluation of Hallucinations in Large-Vision Language Models [57.58426038241812]
  Large Vision-Language Models (LVLMs) have demonstrated remarkable performance in complex multimodal tasks.<n>These models still suffer from hallucinations when required to implicitly recognize or infer diverse visual entities from images.<n>We propose a novel visual question answering (VQA) benchmark that employs contextual reasoning prompts as hallucination attacks.
  arXiv  Detail & Related papers  (2024-12-29T23:56:01Z)
• No Free Lunch: Fundamental Limits of Learning Non-Hallucinating Generative Models [14.535583931446807]
  We develop a theoretical framework to analyze the learnability of non-hallucinating generative models. We show that incorporating inductive biases aligned with the actual facts into the learning process is essential.
  arXiv  Detail & Related papers  (2024-10-24T23:57:11Z)

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.