Rethinking Trust in Human-AI Collaboration in the Generative AI Era
DOI:
https://doi.org/10.58459/icce.2024.4836Abstract
Trust has been thoroughly investigated in human-human collaboration. As large language models advance, human-Al collaboration is becoming the future trend. Generative Al can act as a collaborator. However, limited research dedicated to exploring trust in human-Al collaboration. The degree of trust is intricately connected to both the user's reliance on the system and the system's perceived usefulness. Based on a human- Al collaborative writing dataset, this work employed cluster analysis to explore collaborative patterns in the process of human-Al collaboration. The results show that trust is dynamic, two-sided, and vague element. Meanwhile, based on the changes in trust, human-Al collaboration can be categorized into three types: increasing, curvilinear, and decreasing.