# Evaluating LLM -- Generated Multimodal Diagnosis from Medical Images and Symptom Analysis

arXiv: https://arxiv.org/abs/2402.01730 · HTML: https://mlsanity.com/paper/2402.01730/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 40 references that are in the map.
- First posted on arXiv 28 Jan 2024.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [A Survey on Knowledge Graphs: Representation, Acquisition and Applications](https://mlsanity.com/paper/2002.00388/) (2020)
- [SiT: Self-supervised vIsion Transformer](https://mlsanity.com/paper/2104.03602/) (2021)
- [Domain-specific Knowledge Graphs: A survey](https://mlsanity.com/paper/2011.00235/) (2020)
- [Advances in Medical Image Analysis with Vision Transformers: A Comprehensive Review](https://mlsanity.com/paper/2301.03505/) (2023)
- [Fine-tuning Image Transformers using Learnable Memory](https://mlsanity.com/paper/2203.15243/) (2022)

## Built on by (most cited first, 24 of 24)

- [Agentic Large Language Models, a survey](https://mlsanity.com/paper/2503.23037/) (2025)
- [Securing Large Language Models: Addressing Bias, Misinformation, and Prompt Attacks](https://mlsanity.com/paper/2409.08087/) (2024)
- [Synergizing Foundation Models and Federated Learning: A Survey](https://mlsanity.com/paper/2406.12844/) (2024)
- [A Survey of Medical Vision-and-Language Applications and Their Techniques](https://mlsanity.com/paper/2411.12195/) (2024)
- [Hallucination at a Glance: Controlled Visual Edits and Fine-Grained Multimodal Learning](https://mlsanity.com/paper/2506.07227/) (2025)
- [Leveraging Vision Capabilities of Multimodal LLMs for Automated Data Extraction from Plots](https://mlsanity.com/paper/2503.12326/) (2025)
- [MedOmni-45deg: A Safety-Performance Benchmark for Reasoning-Oriented LLMs in Medicine](https://mlsanity.com/paper/2508.16213/) (2025)
- [Dermacen Analytica: A Novel Methodology Integrating Multi-Modal Large Language Models with Machine Learning in tele-dermatology](https://mlsanity.com/paper/2403.14243/) (2024)
- [COGNET-MD, an evaluation framework and dataset for Large Language Model benchmarks in the medical domain](https://mlsanity.com/paper/2405.10893/) (2024)
- [Advanced Deep Learning and Large Language Models: Comprehensive Insights for Cancer Detection](https://mlsanity.com/paper/2504.13186/) (2025)
- [3DS: Medical Domain Adaptation of LLMs via Decomposed Difficulty-based Data Selection](https://mlsanity.com/paper/2410.10901/) (2024)
- [MpoxVLM: A Vision-Language Model for Diagnosing Skin Lesions from Mpox Virus Infection](https://mlsanity.com/paper/2411.10888/) (2024)
- [Reliable Poisoned Sample Detection against Backdoor Attacks Enhanced by Sharpness Aware Minimization](https://mlsanity.com/paper/2411.11525/) (2024)
- [GENUINE: Graph Enhanced Multi-level Uncertainty Estimation for Large Language Models](https://mlsanity.com/paper/2509.07925/) (2025)
- [Watermarking Large Language Models and the Generated Content: Opportunities and Challenges](https://mlsanity.com/paper/2410.19096/) (2024)
- [Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes](https://mlsanity.com/paper/2507.22940/) (2025)
- [Large language models surpass domain-specific architectures for antepartum electronic fetal monitoring analysis](https://mlsanity.com/paper/2509.18112/) (2025)
- [ClinStructor: AI-Powered Structuring of Unstructured Clinical Texts](https://mlsanity.com/paper/2511.11883/) (2025)
- [An LLM-based Simulation Framework for Embodied Conversational Agents in Psychological Counseling](https://mlsanity.com/paper/2410.22041/) (2024)
- [FedSODA: Federated Fine-tuning of LLMs via Similarity Group Pruning and Orchestrated Distillation Alignment](https://mlsanity.com/paper/2508.12727/) (2025)
- [CataractSurg-80K: Knowledge-Driven Benchmarking for Structured Reasoning in Ophthalmic Surgery Planning](https://mlsanity.com/paper/2508.20014/) (2025)
- [IMCBench: A benchmark for multimodal LLMs in Image-grounded Medical Conversations](https://mlsanity.com/paper/2606.28556/) (2026)
- [SABER: A Semantic-Aligned Brain Network Analysis Framework via Multi-scale Hypergraphs](https://mlsanity.com/paper/2607.01901/) (2026)
- [Sense and Sensitivity: Benchmarking LLM Clinical Triage Recommendations with Physician Experts](https://mlsanity.com/paper/2609.38600/) (2026)

## Abstract (arXiv)

Large language models (LLMs) constitute a breakthrough state-of-the-art Artificial Intelligence technology which is rapidly evolving and promises to aid in medical diagnosis. However, the correctness and the accuracy of their returns has not yet been properly evaluated. In this work, we propose an LLM evaluation paradigm that incorporates two independent steps of a novel methodology, namely (1) multimodal LLM evaluation via structured interactions and (2) follow-up, domain-specific analysis based on data extracted via the previous interactions. Using this paradigm, (1) we evaluate the correctness and accuracy of LLM-generated medical diagnosis with publicly available multimodal multiple-choice questions(MCQs) in the domain of Pathology and (2) proceed to a systemic and comprehensive analysis of extracted results. We used GPT-4-Vision-Preview as the LLM to respond to complex, medical questions consisting of both images and text, and we explored a wide range of diseases, conditions, chemical compounds, and related entity types that are included in the vast knowledge domain of Pathology. GPT-4-Vision-Preview performed quite well, scoring approximately 84% of correct diagnoses. Next, we further analyzed the findings of our work, following an analytical approach which included Image Metadata Analysis, Named Entity Recognition and Knowledge Graphs. Weaknesses of GPT-4-Vision-Preview were revealed on specific knowledge paths, leading to a further understanding of its shortcomings in specific areas. Our methodology and findings are not limited to the use of GPT-4-Vision-Preview, but a similar approach can be followed to evaluate the usefulness and accuracy of other LLMs and, thus, improve their use with further optimization.