2000 character limit reached
User Modeling Challenges in Interactive AI Assistant Systems (2403.20134v1)
Published 29 Mar 2024 in cs.CL
Abstract: Interactive Artificial Intelligent(AI) assistant systems are designed to offer timely guidance to help human users to complete a variety tasks. One of the remaining challenges is to understand user's mental states during the task for more personalized guidance. In this work, we analyze users' mental states during task executions and investigate the capabilities and challenges for LLMs to interpret user profiles for more personalized user guidance.
- Amazon. Alexa, 2023. URL https://alexa.amazon.com/.
- Apple. Siri, 2023. URL https://www.apple.com/siri/.
- Can foundation models watch, talk and guide you step by step to make a cake?, 2023.
- Google. Google assistant, 2023. URL https://assistant.google.com/.
- Ego-exo4d: Understanding skilled human activity from first- and third-person perspectives, 2023.
- A survey on representation learning for user modeling. In Christian Bessiere (ed.), Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI-20, pp. 4997–5003. International Joint Conferences on Artificial Intelligence Organization, 7 2020. doi: 10.24963/ijcai.2020/695. URL https://doi.org/10.24963/ijcai.2020/695. Survey track.
- Holoassist: an egocentric human interaction dataset for interactive ai assistants in the real world, 2023.
- Machine learning for user modeling. User Modeling and User-Adapted Interaction, 11(1):19–29, Mar 2001. ISSN 1573-1391. doi: 10.1023/A:1011117102175. URL https://doi.org/10.1023/A:1011117102175.
- Learning fine-grained view-invariant representations from unpaired ego-exo videos via temporal alignment, 2023.
- Modeling needs user modeling. Frontiers in Artificial Intelligence, 6, 2023. ISSN 2624-8212. doi: 10.3389/frai.2023.1097891. URL https://www.frontiersin.org/articles/10.3389/frai.2023.1097891.