{
  "id": 1281,
  "url": "https://arxiv.org/abs/2606.08800v1",
  "title": "Bridging Expert Knowledge and Automated Feature Engineering via Self-Evolution",
  "summary": "In high-stakes settings such as brand compliance, clinical care, and content moderation, machine learning cannot be deployed as opaque oracles: practitioners inspect the features driving model decisions, and models must leverage the expert documentation governing these domains. In practice, the data arrives as unstructured content, and features extracted from it must be interpretable, discriminative, and aligned with what experts consider important. Existing methods fall short: they target tabul",
  "authors": "Varun Khurana, Vijval Ekbote, Vashu Chauhan, Yaman Kumar Singla, Rajiv Ratn Shah, Balaji Krishnamurthy",
  "category": "research",
  "topics": "bias-fairness,regulation,healthcare",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-07T19:39:03.000Z",
  "fetched_at": "2026-07-14T14:15:07.847Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/1281",
  "original_url": "https://arxiv.org/abs/2606.08800v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}