{
  "id": 18374,
  "url": "https://arxiv.org/abs/2608.09548",
  "title": "ELBench: A Multi-Dimensional Benchmark for Education-Facing Large Language Models",
  "summary": "arXiv:2608.09548v2 Announce Type: replace-cross Abstract: Large language models are increasingly deployed in education as tutors, teaching assistants, and content generators. These roles place demands that ordinary question answering does not: a usable education-facing model is supposed to be accurate, safe under sensitive prompts, instructionally useful, and aligned with pedagogical goals at the same time. Existing benchmarks evaluate these requirements largely in isolation, so none assesses ed",
  "authors": "Yilin Jiang, Xiaorong Zhu, Fei Tan, Zicheng Zhang, Kaiyi Huang, Yang Yu, Zexuan Fei, Yiming Luo, Keqian Li, Hao Hao, Guangtao Zhai, Aimin Zhou",
  "category": "research",
  "topics": "children-education",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-12T04:00:00.000Z",
  "fetched_at": "2026-08-12T05:10:43.828Z",
  "source_slug": "arxiv-cscy",
  "source_name": "arXiv cs.CY",
  "source_homepage": "https://arxiv.org/list/cs.CY/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/18374",
  "original_url": "https://arxiv.org/abs/2608.09548",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}