{"ID":2877081,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.00109","arxiv_id":"2509.00109","title":"Bias Mitigation for AI-Feedback Loops in Recommender Systems: A Systematic Literature Review and Taxonomy","abstract":"Recommender systems continually retrain on user reactions to their own predictions, creating AI feedback loops that amplify biases and diminish fairness over time. Despite this well-known risk, most bias mitigation techniques are tested only on static splits, so their long-term fairness across multiple retraining rounds remains unclear. We therefore present a systematic literature review of bias mitigation methods that explicitly consider AI feedback loops and are validated in multi-round simulations or live A/B tests. Screening 347 papers yields 24 primary studies published between 2019-2025. Each study is coded on six dimensions: mitigation technique, biases addressed, dynamic testing set-up, evaluation focus, application domain, and ML task, organising them into a reusable taxonomy. The taxonomy offers industry practitioners a quick checklist for selecting robust methods and gives researchers a clear roadmap to the field's most urgent gaps. Examples include the shortage of shared simulators, varying evaluation metrics, and the fact that most studies report either fairness or performance; only six use both.","short_abstract":"Recommender systems continually retrain on user reactions to their own predictions, creating AI feedback loops that amplify biases and diminish fairness over time. Despite this well-known risk, most bias mitigation techniques are tested only on static splits, so their long-term fairness across multiple retraining round...","url_abs":"https://arxiv.org/abs/2509.00109","url_pdf":"https://arxiv.org/pdf/2509.00109v1","authors":"[\"Theodor Stoecker\",\"Samed Bayer\",\"Ingo Weber\"]","published":"2025-08-28T09:12:38Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.LG\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false}