算法解释权与算法治理路径研究

Research on the Right to Explanation of Automated Decision-Making and Algorithm Governance

面对日益紧迫的算法治理需求,算法解释权被提出,对用户和相关个体的自治性加以尊重,为用户和相关个体的技术性正当程序权利奠定行使基础、避免算法危害成本外化和弥散。欧盟《通用数据保护条例》在立法层面构建了限制和弱化版本的算法解释权,但通过数据主体权利和数据保护影响评估制度在法律实施层面对其加以补强。但其仍然存在制度构造不足、语句模糊不清、适用范围有限等问题。在构建本土化的算法解释权时,应当明晰算法解释权在算法治理中的地位和功用,厘清其行使要件和核心内容,以社会嵌入性和应用领域为基准探索精准化、场景化的衡量机制,打造内外兼具的技术协同治理机制。

With the increasingly urgent need for algorithm governance,the right to explanation of automated decision-making has been put forward,which has become a ground for empowering users and relevant individuals with respect to their autonomy,the exercise of their technological due process rights,and the avoidance of externalization and shifting of costs and harm caused by algorithm operations.The General Data Protection Regulation(GDPR)designed the right to explanation of automated decisionmaking in a limited and weakened manner,but it created a combined and reinforced version for algorithm explanations by recognizing various rights of both the data subject and the data protection impact assessment mechanism.Nevertheless,the GDPR scheme has several limitations,such as the relevant provisions being made in an incomplete structure,leaving ambiguity and inappropriate limiting of the application scope.When establishing a localized version of the right to an explanation of algorithms,the position and function for algorithm governance should be properly clarified.The major elements and contents of the right should be fully identified,and in accordance with the degree of social embeddedness and specific application fields.An accurate and scenario-based scheme for explanatory measurement should also be introduced,followed by an integrated approach to governance built on collaboration between internal and external actors.