用户可编辑AI解释来定制黑箱模型，实现人机协同决策。
Explanation-Driven Interventions for Artificial Intelligence Model Customization: Empowering End-Users to Tailor Black-Box AI in Rhinocytology
- 用户通过修改AI解释影响模型未来预测
- 无需接触模型内部即可实现个性化调整
- 适合医疗等高风险场景的非技术用户使用
人工智能在现代社会中的集成正在改变人们完成任务的方式。在高风险领域，确保人类对AI系统的控制仍是关键的设计挑战。本文提出一种新型的终端用户开发（EUD）方法，适用于黑箱AI模型，使用户能够通过有针对性的干预编辑解释，并影响未来的预测结果。该方法结合可解释性、用户控制与模型自适应能力，推动以人为本的人工智能（HCAI）发展，促进人类与可适应、用户定制的AI系统之间的共生关系。
原文摘要 · Abstract (English)
The integration of Artificial Intelligence (AI) in modern society is transforming how individuals perform tasks. In high-risk domains, ensuring human control over AI systems remains a key design challenge. This article presents a novel End-User Development (EUD) approach for black-box AI models, enabling users to edit explanations and influence future predictions through targeted interventions. By combining explainability, user control, and model adaptability, the proposed method advances Human-Centered AI (HCAI), promoting a symbiotic relationship between humans and adaptive, user-tailored AI systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。