lightbulb现实痛点机器学习模型可视化、调试与可解释性支持开发者无法有效定位和纠正计算机视觉模型中隐藏的错误。CHI '22How can Explainability Methods be Used to Support Bug Identification in Computer Vision Models?
lightbulb现实痛点机器学习模型可视化、调试与可解释性支持教育技术中,学习工程师难以理解语言模型的摘要评分机制。IUI '24iScore: Visual Analytics for Interpreting How Language Models Automatically Score Summaries
lightbulb现实痛点机器学习模型可视化、调试与可解释性支持医疗领域专业人员难以高效调整数据和优化机器学习模型。CHI '24EXMOS: Explanatory Model Steering through Multifaceted Explanations and Data Configurations
lightbulb现实痛点机器学习模型可视化、调试与可解释性支持开发者难以优化模型以在移动设备上高效运行,同时确保模型准确性。CHI '24Talaria: Interactively Optimizing Machine Learning Models for Efficient Inference
lightbulb现实痛点机器学习模型可视化、调试与可解释性支持用户难以高效修复自然语言转SQL模型生成的错误。IUI '23An Empirical Study of Model Errors and User Error Discovery and Repair Strategies in Natural Language Database Queries
lightbulb现实痛点机器学习模型可视化、调试与可解释性支持团队成员难以了解AutoML系统中“谁在何时做了什么”。CHI '23Tracing and Visualizing Human-ML/AI Collaborative Processes through Artifacts of Data Work
lightbulb现实痛点机器学习模型可视化、调试与可解释性支持医生在使用显著性图时不知道如何理解界面中模型的决策逻辑。CHI '23Graphical Perception of Saliency-based Model Explanations