“Conversational Recommender Systems Using Generative Models (Gen-CRS): A Literature Review”
iCAIML PhD student Ahmadou Wagne has a paper accepted at ACM Transactions on Recommender Systems.
Ahmadou Wagne co-authored the survey paper Conversational Recommender Systems Using Generative Models (Gen-CRS): A Literature Review recently accepted in ACM Transactions on Recommender Systems (TORS). The paper provides a comprehensive review of Generative Conversational Recommender Systems, organizing the field around system architectures and methodologies, knowledge and data foundations, and evaluation practices.
It examines how generative models are transforming conversational recommendation while highlighting key challenges related to grounding, catalog fidelity, controllability, safety, bias, and trustworthy evaluation. The survey also outlines open research directions for developing reliable Gen-CRS.
The publication is available at: https://dl.acm.org/doi/10.1145/3828551