When Retrieval Hurts: Measuring and Explaining Retrieval-Induced Hallucination in Chest X-ray Report Generation

arXiv:2609.31733 · cs.CV · Submitted 2026-09-22 · Read on arXiv

cs.CV

Submitted: 2026-09-22

Updated: 2026-09-22

Terminology

• Hallucination — 19× in this paper · explained in 3 episodes
• Instruction Tuning — 4× in this paper · explained in 2 episodes
• Benchmark — 3× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Embeddings — 2× in this paper · explained in 2 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Retrieval-Guided Cross-Attention — 2× in this paper
• Arbiter — 1× in this paper · explained in 1 episode
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Empirical Methods in Natural Language Processing — 1× in this paper
• Grounding — 1× in this paper · explained in 3 episodes
• Vision-Language Models (VLMs) — 1× in this paper · explained in 6 episodes

Sources

• A Vision-Language Foundation Model to Enhance Efficiency of Chest X-ray Interpretation
• MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• Improved Baselines with Visual Instruction Tuning
• Med-Flamingo: a Multimodal Medical Few-shot Learner
• Object Hallucination in Image Captioning
• BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models