Bias Mitigation for AI-Feedback Loops in Recommender Systems: A Systematic Literature Review and Taxonomy
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918132877099008 |
|---|---|
| author | Stoecker, Theodor Bayer, Samed Weber, Ingo |
| author_facet | Stoecker, Theodor Bayer, Samed Weber, Ingo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_00109 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bias Mitigation for AI-Feedback Loops in Recommender Systems: A Systematic Literature Review and Taxonomy Stoecker, Theodor Bayer, Samed Weber, Ingo Information Retrieval Machine Learning H.3.3; I.2.6; K.4.1 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. |
| title | Bias Mitigation for AI-Feedback Loops in Recommender Systems: A Systematic Literature Review and Taxonomy |
| topic | Information Retrieval Machine Learning H.3.3; I.2.6; K.4.1 |
| url | https://arxiv.org/abs/2509.00109 |