LATIDIA · Investigación

La seguridad como una restricción: ajuste fino de un recomendador de LLM para explicarse a sí mismo

arXiv:2609.13657v1 Tipo de anuncio: nuevo Resumen: Los sistemas de recomendación tradicionales suelen estar entrenados para predecir con qué elemento interactuarán los usuarios a continuación, pero no por qué. Sin embargo, ofrecer evidencia personalizada de por qué un uso

La noticia

arXiv:2609.13657v1 Announce Type: new Abstract: Traditional recommender systems are typically trained to predict what item users will interact with next, but not why. However, offering personalized evidence for why a user might like the predicted item is an important way to enhance the service and to raise the likelihood that the user will be genuinely interested in the recommendation. This service can be delivered by integrating a frontier-model call into the member-facing pipeline, but it will add extra cost and latency. In this paper, we train a recommender LLM to generate personalized explanations for its reccomendation, based on the user's watching history at a large video streaming service. We impose