首页 > AI前沿 > SteerGR: Steering Generative Recommendation via Sparse Autoencoders for Controllable Game Discovery

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

arXiv自然语言 2026-11-06 07:25 17 阅读 查看原文

Generative recommendation aims to predict item identifiers from user interaction histories, but explicit control over the properties of recommended items remains underexplored. A key challenge is to connect human-readable concepts to internal features whose interventions effectively change the recommended items. To address this, we propose Steerable Generative Recommender (SteerGR), a framework that uses sparse autoencoders for concept-level control in game discovery.

SteerGR proceeds through three stages:

  • Concept Definition and Grounding for defining play concepts with an LLM;
  • Feature Discovery and Selection for discovering candidate features by their concept associations and selecting one by its steering effect;
  • Sparse Feature Intervention for amplifying or suppressing selected features to steer recommendations without retraining the recommender.

Extensive experiments with two industrial generative recommendation models on a real-world game dataset show that the selected features successfully steer recommendations toward or away from target concepts. We believe this work takes a first step to extend SAE-based steering from LLMs to industrial generative recommendation.