Reproducing Transparent and Scrutable Recommendations: Exploring Open-Weight Models via Natural-Language User Profiles
This paper explores using open-weight language models with natural-language user profiles to make recommender systems more transparent and scrutable, a modest technical contribution with no immediate risk or mitigation implications.
This paper explores using open-weight language models with natural-language user profiles to make recommender systems more transparent and scrutable, a modest technical contribution with no immediate risk or mitigation implications.
Auto-scored: A standard academic paper on transparent recommendation methods, with no direct safety, misuse, or governance impact.