SteerGR: Steering Generative Recommendation via Sparse Autoencoders for Controllable Game Discovery

SteerGR is a framework that enables concept-level control in generative recommendation for game discovery. It uses sparse autoencoders to define play concepts with an LLM, discover and select features associated with those concepts, and then intervene on the selected features to steer recommendations without retraining the model. Experiments on two industrial generative recommendation models demonstrate that the selected features can successfully steer recommendations toward or away from target concepts.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• llms