User Interaction Dataset for Hypertext 2024 paper "To Err Is AI! Debugging as an Intervention to Facilitate Appropriate Reliance on AI Systems."

This repo contains code and data associated with the paper "To Err Is AI! Debugging as an Intervention to Facilitate Appropriate Reliance on AI Systems." In our study, we asked participants to detect whether one piece of hotel reviews was generated by real customers or faked. We provide explanations as text highlights generated with BERT-LIME. In the debugging tutorial stage, participants are asked to adjust the model explanation and guess its correctness.

本代码仓库包含与论文《犯错亦为AI！以调试作为干预手段以促进对人工智能（AI）系统的合理信赖》相关的代码与数据集。本研究中，我们要求参与者判别单条酒店评论为真实顾客撰写还是伪造生成。我们提供了由BERT-LIME生成的文本高亮形式的模型解释。在调试教程环节中，参与者需调整该模型解释，并猜测其正确性。