{
  "id": 3643,
  "url": "https://arxiv.org/abs/2605.27710v1",
  "title": "DeepSciVerify: Verifying Scientific Claim--Citation Alignment via LLM-Driven Evidence Escalation",
  "summary": "Misalignment between claims and their cited evidence is a common failure mode in reports generated by large language models, limiting their reliability in scientific and other high-stakes settings. We present DeepSciVerify, a two-stage pipeline for scientific claim-citation verification that combines abstract-level reasoning with selective escalation to passage-level evidence. The system first verifies claims using the abstract and defers uncertain cases, retrieving and analyzing full-text passa",
  "authors": "Shaghayegh Sadeghi, Khashayar Khajavi, Rise Adhikari, Alexander Tessier",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-26T21:33:29.000Z",
  "fetched_at": "2026-07-14T16:30:23.247Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/3643",
  "original_url": "https://arxiv.org/abs/2605.27710v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}