{
  "id": 1242,
  "url": "https://arxiv.org/abs/2606.10126v1",
  "title": "Pareto-Guided Teacher Alignment for Fair Personalized Text Generation",
  "summary": "Personalized persuasive text generation can improve relevance and engagement, but demographic conditioning may also introduce unequal framing across groups. We study fairness mitigation in personalized generation as a constrained multi-objective alignment problem: reduce demographic disparities while preserving personalization fidelity. We propose a Pareto-guided teacher alignment framework that combines revision-based candidate generation, pair-aware feasibility gating, Pareto-style candidate s",
  "authors": "Tunazzina Islam",
  "category": "research",
  "topics": "bias-fairness,safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-08T19:57:13.000Z",
  "fetched_at": "2026-07-14T14:15:07.845Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/1242",
  "original_url": "https://arxiv.org/abs/2606.10126v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}