{
  "id": 5612,
  "url": "https://arxiv.org/abs/2604.18660v1",
  "title": "Evaluating Answer Leakage Robustness of LLM Tutors against Adversarial Student Attacks",
  "summary": "Large Language Models (LLMs) are increasingly used in education, yet their default helpfulness often conflicts with pedagogical principles. Prior work evaluates pedagogical quality via answer leakage-the disclosure of complete solutions instead of scaffolding-but typically assumes well-intentioned learners, leaving tutor robustness under student misuse largely unexplored. In this paper, we study scenarios where students behave adversarially and aim to obtain the correct answer from the tutor. We",
  "authors": "Jin Zhao, Marta Knežević, Tanja Käser",
  "category": "research",
  "topics": "children-education,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-20T11:29:22.000Z",
  "fetched_at": "2026-07-14T16:31:53.166Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5612",
  "original_url": "https://arxiv.org/abs/2604.18660v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}