A Design Space for Explainable Ranking and Ranking Models
원문 초록
Item ranking systems support users in multi-criteria decision-making tasks. Users need to trust rankings and ranking algorithms to reflect user preferences nicely while avoiding systematic errors and biases. However, today only few approaches help end users, model developers, and analysts to explain rankings. We report on the study of explanation approaches from the perspectives of recommender systems, explainable AI, and visualization research and propose the first cross-domain design space for explainers of item rankings. In addition, we leverage the descriptive power of the design space to characterize a) existing explainers and b) three main user groups involved in ranking explanation tasks. The generative power of the design space is a means for future designers and developers to create more target-oriented solutions in this only weakly exploited space.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
LLM-Stackelberg Games: Conjectural Reasoning Equilibria and Their Applications to Spearphishing
A Simple Contrastive Framework Of Item Tokenization For Generative Recommendation
Asymmetric Transitivity Preserving Graph Embedding
Graph-Structured Data Analysis of Component Failure in Autonomous Cargo Ships Based on Feature Fusion
A Reproducibility Study of Product-side Fairness in Bundle Recommendation
Describe Anything Model for Visual Question Answering on Text-rich Images
토론
이 논문과 연결된 포럼 글이 아직 없습니다.