{
  "id": 673,
  "url": "https://arxiv.org/abs/2606.24042v1",
  "title": "Breaking the Filter Bubble: A Semantic Pareto-DQN Framework for Multi-Objective Recommendation",
  "summary": "Recommender systems often induce filter bubbles and semantic homogenization by monolithically optimizing for immediate user engagement. Standard single-objective models, including traditional Deep Q-Networks, are ill-equipped to navigate the trade-offs between platform retention and critical societal values like information diversity and provider fairness. To address these limitations, we introduce a multi-objective reinforcement learning framework that formalizes recommendation as a semantic mu",
  "authors": "Cláudio Lúcio Do Val Lopes, Lucca Machado da Silva, André de Oliveira Brandão",
  "category": "research",
  "topics": "bias-fairness",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-23T00:58:16.000Z",
  "fetched_at": "2026-07-14T14:14:41.552Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/673",
  "original_url": "https://arxiv.org/abs/2606.24042v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}