{
  "id": 12350,
  "url": "https://arxiv.org/abs/2607.18725v1",
  "title": "Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA",
  "summary": "Large Language Models (LLMs) are increasingly fine-tuned for critical-domain Question-Answering (QA), yet choosing which small model to adapt, before paying the cost of adaptation, remains difficult. Fine-tuning can improve domain alignment, but it may also erode prior knowledge, weaken instruction-following, or increase hallucination, especially when labeled data are scarce or rapidly evolving as in cybersecurity. We present FiT (Find before Fine-Tune), a task-oriented diagnostic framework that",
  "authors": "Shaswata Mitra, Subash Neupane, Trisha Chakraborty, Himanshu Tripathi, Sudip Mittal, Aritran Piplai et al.",
  "category": "research",
  "topics": "safety-alignment,healthcare",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-21T05:32:40.000Z",
  "fetched_at": "2026-07-22T05:10:49.469Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/12350",
  "original_url": "https://arxiv.org/abs/2607.18725v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}