{
  "id": 1312,
  "url": "https://arxiv.org/abs/2606.08400v1",
  "title": "Impacts of Histories and Models on LLM Grading: A Study in Advanced Software Engineering Courses",
  "summary": "Graduate-level research reading report assessment creates a substantial labor burden for educators. While large language models (LLMs) hold great potential for automating academic grading, their reliability for this specialized task remains understudied, particularly regarding grading consistency, the lack of which represents a primary obstacle to educational fairness. This paper proposes a human-aligned LLM-assisted grading workflow and presents a case study based on 180 student submissions fro",
  "authors": "Qilin Zhou, Zhuo Wang, Yue Li, W. K. Chan",
  "category": "research",
  "topics": "bias-fairness,jobs-economy,children-education",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-07T01:31:23.000Z",
  "fetched_at": "2026-07-14T14:15:12.455Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/1312",
  "original_url": "https://arxiv.org/abs/2606.08400v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}