Explainable Recommendations at Scale: LLM Rationales for YouTube Music Artist Discovery
This paper presents an industry case study of a decoupled recommendation architecture that successfully scales exploration without compromising latency, and demonstrates that combining LLM-backed recommendations with these explanatory rationales significantly reduces the trust barrier for new content.
Xiao Liu, Yan-Wei Song, Srivaths Ranganathan et al.
· 0 citations