Metraipolis › archive › dc_f815580553bd
SteerGR: Steering Generative Recommendation via Sparse Autoencoders for Controllable Game Discovery — arXiv:2611.08790
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.08790
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-09T22:34:37.335Z
- SHA-256 of the archived text
3e6d23f70cf3cd725c34cebe73a2229bb540e62dc07e1e6485325c9b7c9b0bfd- Stable URL of this page
https://metraipolis.com/documento/dc_f815580553bd
How to cite
SteerGR: Steering Generative Recommendation via Sparse Autoencoders for Controllable Game Discovery — arXiv:2611.08790 — arXiv (en), https://arxiv.org/abs/2611.08790 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f815580553bd (Metraipolis archive dc_f815580553bd, sha256 3e6d23f70cf3cd725c34cebe73a2229bb540e62dc07e1e6485325c9b7c9b0bfd)
BibTeX
@misc{dcf815580553bd,
title = {SteerGR: Steering Generative Recommendation via Sparse Autoencoders for Controllable Game Discovery — arXiv:2611.08790},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.08790},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f815580553bd; sha256 3e6d23f70cf3cd725c34cebe73a2229bb540e62dc07e1e6485325c9b7c9b0bfd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08790. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2611.08790 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-09T22:30:47.308Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).