Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Shim, Alexander, Saieh, Khalil, Clarke, Samuel
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2601.08226
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911371436752896
author Shim, Alexander
Saieh, Khalil
Clarke, Samuel
author_facet Shim, Alexander
Saieh, Khalil
Clarke, Samuel
contents This research analyzed and compared the multi-modal approach in the Vision Transformer(EVA-ViT) based image encoder with the LlaMA or ChatGPT LLM to reduce the hallucination problem and detect diseases in chest x-ray images. In this research, we utilized the NIH Chest X-ray image to train the model and compared it in image-based RAG, text-based RAG, and baseline. [3] [5] In a result, the text-based RAG[2] e!ectively reduces the hallucination problem by using external knowledge information, and the image-based RAG improved the prediction con"dence and calibration by using the KNN methods. [4] Moreover, the GPT LLM showed better performance, a low hallucination rate, and better Expected Calibration Error(ECE) than Llama Llama-based model. This research shows the challenge of data imbalance, a complex multi-stage structure, but suggests a large experience environment and a balanced example of use.
format Preprint
id arxiv_https___arxiv_org_abs_2601_08226
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Knowledge-based learning in Text-RAG and Image-RAG
Shim, Alexander
Saieh, Khalil
Clarke, Samuel
Computer Vision and Pattern Recognition
Artificial Intelligence
This research analyzed and compared the multi-modal approach in the Vision Transformer(EVA-ViT) based image encoder with the LlaMA or ChatGPT LLM to reduce the hallucination problem and detect diseases in chest x-ray images. In this research, we utilized the NIH Chest X-ray image to train the model and compared it in image-based RAG, text-based RAG, and baseline. [3] [5] In a result, the text-based RAG[2] e!ectively reduces the hallucination problem by using external knowledge information, and the image-based RAG improved the prediction con"dence and calibration by using the KNN methods. [4] Moreover, the GPT LLM showed better performance, a low hallucination rate, and better Expected Calibration Error(ECE) than Llama Llama-based model. This research shows the challenge of data imbalance, a complex multi-stage structure, but suggests a large experience environment and a balanced example of use.
title Knowledge-based learning in Text-RAG and Image-RAG
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2601.08226