LLM Integrated Application
LLM-integrated applications leverage large language models (LLMs) like GPT-4 and Llama-2 to enhance existing software or create entirely new functionalities across diverse domains, from e-commerce to agriculture. Current research emphasizes improving LLM outputs through techniques such as automated editing and tailored prompt engineering, while also addressing critical issues like bias mitigation, security vulnerabilities (including prompt injection and leakage), and the development of robust evaluation frameworks. This rapidly evolving field is significant because it not only pushes the boundaries of AI capabilities but also necessitates the development of new methods for ensuring responsible and secure deployment of these powerful technologies in various applications.
Papers
LLM-TS Integrator: Integrating LLM for Enhanced Time Series Modeling
Can Chen, Gabriel Oliveira, Hossein Sharifi Noghabi, Tristan Sylvain
Developing Retrieval Augmented Generation (RAG) based LLM Systems from PDFs: An Experience Report
Ayman Asad Khan, Md Toufique Hasan, Kai Kristian Kemell, Jussi Rasku, Pekka Abrahamsson
Procedural Content Generation in Games: A Survey with Insights on Emerging LLM Integration
Mahdi Farrokhi Maleki, Richard Zhao