{
  "id": 5891,
  "url": "https://arxiv.org/abs/2604.12337v1",
  "title": "Identifying and Mitigating Gender Cues in Academic Recommendation Letters: An Interpretability Case Study",
  "summary": "Letters of recommendation (LoRs) can carry patterns of implicitly gendered language that can inadvertently influence downstream decisions, e.g. in hiring and admissions. In this work, we investigate the extent to which Transformer-based encoder models as well as Large Language Models (LLMs) can infer the gender of applicants in academic LoRs submitted to an U.S. medical-residency program after explicit identifiers like names and pronouns are de-gendered. While using three models (DistilBERT, RoB",
  "authors": "Charlotte S. Alexander, Shane Storks, Souradip Pal, Sayak Chakrabarty, Arushi Sharma, Mlen-Too Wesley et al.",
  "category": "research",
  "topics": "safety-alignment,healthcare,finance-investment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-14T06:19:35.000Z",
  "fetched_at": "2026-07-14T16:32:06.467Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5891",
  "original_url": "https://arxiv.org/abs/2604.12337v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}