Research Area:  Machine Learning

Abstract:

Large language models have experienced a significant transformation with the advent of powerful models capable of generating, translating, and summarizing text. However, effectively integrating and reasoning with multimodal data, which includes text, images, and audio, continues to pose a formidable challenge. The novel concept of federated example selection, as proposed in this paper, is significant because it addresses critical issues of data privacy, diversity, and representation, thus enhancing multimodal reasoning capabilities in AI models. By modifying the open-source LLM, Llama, with a federated example selection algorithm, this research demonstrates substantial improvements in model performance across various tasks. The methodology involves a comprehensive approach that includes secure data collection, algorithm design, and iterative model refinement, all within a federated learning framework. The experimental results indicate notable advancements in accuracy, precision, recall, and F1-score, outperforming state-of-the-art models and showcasing the algorithms efficacy. Additionally, scalability analysis confirms the algorithms ability to handle large-scale datasets efficiently, while ablation studies highlight the importance of each algorithmic component. The findings suggest that the proposed methodology not only enhances the integration of diverse data types but also paves the way for future developments in multimodal AI, demonstrating the transformative potential of federated learning approaches.

Keywords:  

Author(s) Name:  Beatrice Fawcett, Felix Ashworth, Harriet Dunbar

Publisher name:  ResearchGate

DOI:  10.21203/rs.3.rs-4745818/v1

Volume Information:  volume 83,(2024)

Paper Link:   https://www.researchgate.net/publication/382328298_Improving_Multimodal_Reasoning_in_Large_Language_Models_via_Federated_Example_Selection