{"type":"ScholarlyArticle","title":"You Don't Bring Me Flowers: Mitigating Unwanted Recommendations Through Conformal Risk Control (Extended Abstract)","authors":[{"name":"Giovanni De Toni","slug":"giovanni-de-toni","given":"Giovanni","family":"De Toni","affiliation":""},{"name":"Erasmo Purificato","slug":"erasmo-purificato","given":"Erasmo","family":"Purificato","affiliation":""},{"name":"Emilia Gómez","slug":"emilia-gomez","given":"Emilia","family":"Gómez","affiliation":""},{"name":"Andrea Passerini","slug":"andrea-passerini","given":"Andrea","family":"Passerini","affiliation":""},{"name":"Bruno Lepri","slug":"bruno-lepri","given":"Bruno","family":"Lepri","affiliation":""},{"name":"Cristian Consonni","slug":"cristian-consonni","given":"Cristian","family":"Consonni","affiliation":""}],"abstract":"Recommenders are significantly shaping online information consumption. While effective at personalizing content, these systems increasingly face criticism for propagating irrelevant, unwanted, and even harmful recommendations. Such content degrades user satisfaction and contributes to significant societal issues, including misinformation, radicalization, and erosion of user trust. Although platforms offer mechanisms to mitigate exposure to undesired content, these mechanisms are often insufficiently effective and slow to adapt to users' feedback. This paper introduces an intuitive, model-agnostic, and distribution-free method that uses conformal risk control to provably bound unwanted content in personalized recommendations by leveraging simple binary feedback on items. We also address a limitation of traditional conformal risk control approaches, i.e., the fact that the recommender can provide a smaller set of recommended items, by leveraging implicit feedback on consumed items to expand the recommendation set while ensuring robust risk mitigation. Our experimental evaluation on data coming from a popular online video-sharing platform demonstrates that our approach ensures an effective and controllable reduction of unwanted recommendations with minimal effort.","doi":"10.24963/ijcai.2026/923","url":"https://ijcai.org/proceedings/2026/923","pdf":"https://ijcai.org/proceedings/2026/0923.pdf","markdown":"https://ijcai.org/proceedings/2026/923.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/923","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Sister Conferences Best Papers","track":"Sister Conferences Best Papers","number":923,"pages":{"first":8260,"last":8265},"keywords":["AI: Uncertainty in AI","Data Mining: Recommender systems","AI Ethics, Trust, Fairnes: Societal impact of AI","AI: Machine Learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}