Affiliation:
1. Centre for Cognitive Science, Technical University of Darmstadt, Germany
Abstract
Designing cooperative AI-systems that do not automate tasks but rather aid human cognition is challenging and requires human-centered design approaches. Here, we introduce AI-aided brainstorming for solving guesstimation problems, i.e. estimating quantities from incomplete information, as a testbed for human-AI interaction with large language models (LLMs). In a think-aloud study, we found that humans decompose guesstimation questions into sub-questions and often replace them with semantically related ones. If they fail to brainstorm related questions, they often get stuck and do not find a solution. Therefore, to support this brainstorming process, we prompted a large language model (GPT-3) with successful replacements from our think-aloud data. In follow-up studies, we tested whether the availability of this tool improves participants’ answers. While the tool successfully produced human-like suggestions, participants were reluctant to use it. From our findings, we conclude that for human-AI interaction with LLMs to be successful AI-systems must complement rather than mimic a user’s associations.
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Temporal Aspects of Human-AI Collaborations for Work;Proceedings of the 3rd Annual Meeting of the Symposium on Human-Computer Interaction for Work;2024-06-25
2. Serendipity Wall: A Discussion Support System Using Real-time Speech Recognition and Large Language Model;Proceedings of the Augmented Humans International Conference 2024;2024-04-04