Publication
The Interactive Deep Learning Enterprise (No-IDLE) meets ChatGPT
Daniel Sonntag; Thiago Gouvea; Michael Barz; Aliki Anagnostopoulou; Siting Liang; Sara-Jane Bittner; Franziska Scheurer
Deutsches Forschungszentrum für Künstliche Intelligenz GmbH, DFKI Technical Report, 2024.
Abstract
This DFKI technical report presents the anatomy of the No-IDLE meets ChatGPT prototype system (funded by the German Federal
Ministry of Education and Research) that provides not only basic and fundamental research in interactive machine learning, but
also reveals deeper insights into how to leverage the opportunities arising from large language models and technologies for the
No-IDLE project. No-IDLE’s goals and scientific challenges centre around the desire to increase the reach of interactive deep learning
solutions for non-experts in machine learning. No-IDLE aims to enhance the interaction between humans and machines for the
purpose of updating deep learning models, integrating cutting-edge human-computer interaction techniques and advanced deep
learning approaches. Considering the recent advances in LLMs and their multimodal capabilities, the overall objective of "No-IDLE
meets ChatGPT" should be well motivated. One of the key innovations described in this technical report is a methodology including
benchmark studies for interactive machine learning combined with LLMs which will become central when we start interacting with
semi-intelligent machines based on optimisation methods like automatic prompt engineering or natural language inference. Our main
research question is how ChatGPT and other variants can help improve the accuracy of (semi-) automatic subtasks in image retrieval,
captioning, and person/scene recognition.