Overview

Automated grading studies how to assess student work consistently, from short answers and essays to mathematical reasoning, handwritten exams, and programming assignments. Approaches include fine-tuned language models and encoders, rubric-guided LLM judges, and vision-language systems that read handwritten work; many combine scores with explanations or route uncertain cases to human graders. Systems are commonly evaluated against expert marks using agreement and error measures, with benchmarks testing transfer across subjects, questions, and scoring rubrics. A central challenge is handling partial or ambiguous answers reliably while avoiding bias, prompt sensitivity, and overconfidence, so human oversight remains important, especially for high-stakes decisions.

Latest papers

CardsList

98 papers7 papers in the last four weeks, down 12% on the four weeks before. 0.1% of all new papers.

  1. Evaluating AI Grading on Real-World Handwritten College Mathematics: A Large-Scale Study Toward a Benchmark

    Mar 1, 2026Zhiqi Yu, Xingping Liu, Haobin Mao +4Automated GradingGenerative AI in Education

  2. Optimizing In-Context Demonstrations for LLM-based Automated Grading

    Feb 28, 2026Yucheng Chu, Hang Li, Kaiqi Yang +4EducationAutomated Grading

  3. From Flat to Structural: Enhancing Automated Short Answer Grading with GraphRAG

    Feb 28, 2026Yucheng Chu, Haoyu Han, Shen Dong +6Automated GradingEducational Assessment

  4. Confusion-Aware Rubric Optimization for LLM-based Automated Grading

    Feb 28, 2026Yucheng Chu, Hang Li, Kaiqi Yang +4Automated GradingPrompt Optimization

  5. Toward LLM-Supported Automated Assessment of Critical Thinking Subskills

    Oct 14, 2025Marisa C. Peczuh, Nischal Ashok Kumar, Ryan Baker +11Educational AssessmentAutomated Grading