Pith. sign in

REVIEW 4 cited by

Reducing Hallucinations of Medical Multimodal Large Language Models with Visual Retrieval-Augmented Generation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.15040 v1 pith:HZNIDVW4 submitted 2025-02-20 cs.CL cs.AI

Yun-Wei Chu , Kai Zhang , Christopher Malon , Martin Renqiang Min This is my paper
classification cs.CLcs.AI
keywords generationvisualmedicaldataentitiesentityhallucinationsimage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Multimodal Large Language Models (MLLMs) have shown impressive performance in vision and text tasks. However, hallucination remains a major challenge, especially in fields like healthcare where details are critical. In this work, we show how MLLMs may be enhanced to support Visual RAG (V-RAG), a retrieval-augmented generation framework that incorporates both text and visual data from retrieved images. On the MIMIC-CXR chest X-ray report generation and Multicare medical image caption generation datasets, we show that Visual RAG improves the accuracy of entity probing, which asks whether a medical entities is grounded by an image. We show that the improvements extend both to frequent and rare entities, the latter of which may have less positive training data. Downstream, we apply V-RAG with entity probing to correct hallucinations and generate more clinically accurate X-ray reports, obtaining a higher RadGraph-F1 score.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. HalluScope: Fine-grained Hallucination Diagnosis for Multimodal Large Language Models

    cs.CV 2026-07 conditional novelty 6.0 of 10

    HalluScope couples span-level hallucination detection, 12-way type classification, and explanation generation in one model, and shows the resulting feedback reduces hallucinations in two MLLMs.

  2. TerraMAE: Learning Spatial-Spectral Representations from Hyperspectral Earth Observation Data via Adaptive Masked Autoencoders

    cs.CV 2025-08 reject novelty 5.0 of 10

    The abstract proposes TerraMAE, an adaptive channel-grouping masked autoencoder for hyperspectral Earth observation, but the manuscript body is a different paper, leaving the proposal without any supporting method or ...

  3. MedVQA-TREE: A Multimodal Reasoning and Retrieval Framework for Sarcopenia Prediction

    eess.IV 2025-08 reject novelty 4.0 of 10

    MedVQA-TREE fuses three levels of ultrasound image features with UMLS-guided PubMed retrieval to predict sarcopenia, reporting 99% accuracy on a 24-patient proprietary dataset.

  4. Trustworthy Medical Imaging with Large Language Models: A Study of Hallucinations Across Modalities

    eess.IV 2025-08 conditional novelty 4.0 of 10

    AI models hallucinate when reading medical images and when generating them from text, producing false findings and anatomically impossible pictures.

Pith tools