cs.IRNov 5, 2026

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

Authors: Sunkyung Lee, Xiaokai Wei, Da Long, Hyunsik Jeon, Jiajun Wu, Rithwik Seth, Jongwuk Lee, Michelle Gong, 

Organizations: Sungkyunkwan University, Republic of Korea · Roblox Corporation, USA

Abstract

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: (i) Concept Definition and Grounding for defining play concepts with an LLM; (ii) Feature Discovery and Selection for discovering candidate features by their concept associations and selecting one by its steering effect; and (iii) 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.

Figures & tables

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. RecoGEM: A Serving System for Production-Scale Generative Recommendation

    Nov 9, 2026Xiangrui Yang, Yunfeng Zhao, Jiawei Yang +8Recommender SystemsGenerative Recommendation

  2. The Vocabulary Is Already Here: Adapting Pretrained Interpretable Features for Generative Recommendation

    Oct 27, 2026Ziluowen Luo, Ruochen Liu, Jun Yin +6Generative RecommendationSemantic ID Recommendation

  3. Think Globally, Generate Personally: Multi-View Thinking with Adaptive Generation for Generative Recommendation

    Nov 2, 2026Yuxuan Hu, Yingyi Zhang, Wenlin Zhang +11Generative RecommendationSemantic ID Recommendation