“EMO” personal emotional assistant using cache based retrieval augmented generation chain
Abstract
Currently, Retrieval-Augmented Generation (RAG) introduces latency in retrieval and generating response. Cache-Augmented Generation (CAG) generates contextual response quickly by searching in knowledge cache, and solves the latency problem, however, the the size of the cache is limited and not preferred for generic retrieval scenarios. The paper proposes a personal emotional assistant (EMO) using a hybrid approach of RAG and CAG in a generative AI application. The EMO handles user emotions and provides coherent, context-sensitive guidance by leveraging advanced language models and embedding techniques. The EMO includes fine-tuning language models on healthcare-specific data and integrating a dynamic retrieval mechanism to ensure that the responses are accurate, fast but also empathetic and supportive. Comprehensive experiment analysis has been performed to evaluate EMO performance with 95% accuracy in various scenarios, including stress management, mental health support, chronic illness management, and general wellness advice. User feedback was collected through surveys and interaction logs, demonstrating high levels of user engagement and perceived supportiveness.
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.