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

David Iagaru; Nina M. Gottschling; Anders C. Hansen; Josselin Garnier

stat.MLMay 13, 2026

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

Authors: David Iagaru, Nina M. Gottschling, Anders C. Hansen, Josselin Garnier

Organizations: CMAP, Ecole polytechnique, Institut Polytechnique de Paris, 91120 Palaiseau, France. · German Aerospace Center (DLR), Remote Sensing Technology Institute, Wessling, Germany. · Computing and Computational Sciences, Oak Ridge National Laboratory, Oak Ridge, Tennessee. · DAMTP, University of Cambridge, Cambridge, UK · CMAP, CNRS, Ecole polytechnique, Institut Polytechnique de Paris, 91120 Palaiseau, France.

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.

Explore similar work

Hallucination in Medical Imaging AI: A Cross-Modality Analytical Framework for Taxonomy, Detection, and Mitigation under Regulatory Constraints
Jun 11, 2026Omar Alshahrani, Muzammil BehzadHallucinations Medical Imaging
Does Playing it Safe Count as Faithfulness? Reassessing LVLM Hallucination Mitigation Methods
Sep 1, 2026Mehrdad Fazli, Sina Mansouri, Mohit Marvania +1Large Language Model Hallucination Hallucination Mitigation
Hallucination-Aware Diffusion Sampling for Inverse Problems via Robust Prior Updates
Jun 1, 2026Pengfei Jin, Yiqi Tian, Kailong Fan +2Diffusion Priors Ill-Posed Inverse Problem

Jun 11, 2026 · cs.AIJ/K move · Enter open · S save

Hallucination in Medical Imaging AI: A Cross-Modality Analytical Framework for Taxonomy, Detection, and Mitigation under Regulatory Constraints

Omar Alshahrani, Muzammil Behzad

King Fahd University of Petroleum & Minerals, Saudi Arabia · SDAIA-KFUPM Joint Research Center for Artificial Intelligence, Saudi Arabia

AI systems are being deployed across medical imaging faster than their failure modes are understood. At this point in time, the failure of greatest clinical concern is hallucination: clinically plausible but factually incorrect outputs, including fabricated anatomical structures, missed findings, incorrect laterality, and invented measurements in generated reports, with direct consequences, for example, for biopsy decisions, staging, and treatment planning. This structured narrative synthesizes peer-reviewed studies, benchmark datasets, and FDA regulatory guidance across five imaging modalities to produce a cross-modality analysis of hallucination taxonomy, etiology, detection, and mitigation. Specifically, we address three questions in this study: (1) how can existing taxonomies be unified across modalities?, (2) how do medical-specialized foundation models hallucinate less than general-purpose ones?, and (3) which mitigation strategies are effective and compatible with FDA lifecycle oversight? We note that three taxonomic frameworks together cover the imaging pipeline in a way no single framework does alone. We also highlight that general-purpose foundation models outperform medical-specialized models on hallucination-specific benchmarks, indicating that narrow domain fine-tuning can introduce overfitting-induced confabulation. At the same time, the oversight of radiologists remains essential; for instance, a very high percentage of of AI-generated flags required expert correction before clinical use. Physics-informed architectural constraints, Chain-of-Thought prompting, and human-in-the-loop safeguards each address different failure modes and is effective when combined. All findings are mapped to the FDA's Total Product Lifecycle and Predetermined Change Control Plan frameworks, which treat hallucination management as a lifecycle obligation rather than a pre-deployment checklist.

Hallucinations Medical Imaging Multimodal Clinical Data Cross-Modality Multimodal Artificial Intelligence Wireless Foundation Models Scalable Oversight Taxonomy

Open paper Ask about it PDF

Abstract

Explore similar work

Hallucination in Medical Imaging AI: A Cross-Modality Analytical Framework for Taxonomy, Detection, and Mitigation under Regulatory Constraints

Does Playing it Safe Count as Faithfulness? Reassessing LVLM Hallucination Mitigation Methods

Hallucination-Aware Diffusion Sampling for Inverse Problems via Robust Prior Updates