Close

Presentation

Chatbot Memory: Uncovering How Mental Effort and Chabot Interactions Affect Short-Term Learning
DescriptionDevelopments in artificial intelligence (AI) disrupt our ways of living. Generative AI is particularly representative of these changes as it can generate content traditionally reserved to humans with increased efficiency and reduced effort. This includes technologies like ChatGPT and other tools that exploit large language models, typically taking the form of conversational agents (chatbots) that understand natural language and produce responses accordingly. These technologies can be useful for self-regulated learning as is the case for Web browsing and other Web-based tools. It is however unclear whether learning with chatbots may be efficient as opposed to other Web-based approaches given the reduced effort related with chatbot interactions. This study assessed how chatbot interactions affect short-term learning and what role plays mental effort. We report impacts on memory and self-reported workload of participants gathering information from the Internet or from a chatbot for answering essay questions, followed by a surprise memory test.