Yijia Dai

Language-Based User Profiles for Recommendation

2024 · arXiv (Cornell University)

Most conventional recommendation methods (e.g., matrix factorization) represent user profiles as high-dimensional vectors. Unfortunately, these vectors lack interpretability and steerability, and often perform poorly in cold-start settings. To address these shortcomings, we explore the use …

End-to-end Training for Recommendation with Language-based User Profiles

2024 · arXiv (Cornell University)

There is a growing interest in natural language-based user profiles for recommender systems, which aims to enhance transparency and scrutability compared with embedding-based methods. Existing studies primarily generate these profiles using zero-shot inference from large …