Search papers, labs, and topics across Lattice.
This study evaluates the effectiveness of four large language models (LLMs) in grading Linux/bash command-line examinations using a four-level cognitive taxonomy that assesses cognitive complexity and operational impact. By analyzing 1200 student responses graded by expert instructors, the research found that Gemini 3.0 Pro with rubric-guided prompting achieved the highest agreement with human grading, particularly at lower cognitive levels. The findings highlight that question complexity significantly influences LLM grading accuracy and provide a framework for determining the suitability of AI-assisted grading versus human review.
LLMs can achieve near-expert grading accuracy for command-line exams, but their performance declines sharply with question complexity.
Scalable and reliable grading of command-line examinations remains a challenge in computing education, where rising enrolments make manual marking difficult and rule-based autograders cannot handle partial credit, equivalent solutions, or syntactic variation. This paper evaluates whether four frontier Large Language Models (GPT, Claude Opus, Gemini, and GLM) can approximate expert judgment when grading short Linux/bash command responses. The study adopts a four-level cognitive taxonomy that combines cognitive complexity and operational impact, ranging from information retrieval (L1) and basic file manipulation (L2) to structural operations (L3) and advanced system management (L4). The models were tested with two prompt variants, a minimal baseline and a rubric-enhanced version, on 1200 real responses from second-year Computer Engineering students independently graded by three expert instructors. Gemini~3.0 Pro with rubric-guided prompting achieved the highest human-AI agreement (ICC(3,1) = 0.888, MAE = 0.10, Bland-Altman bias = -0.014). Agreement declined consistently as taxonomy level increased, with the largest discrepancies at higher levels. Across all models, rubric quality had a larger effect than provider choice, with structured prompts consistently improving agreement. These results show that question complexity is a reliable predictor of the difficulty LLMs face in grading accurately, and they establish a principled, taxonomy-based framework for determining which questions are suitable for AI-assisted grading and which require human review, while also providing a transferable evaluation protocol and prompt templates.
