Evaluating Generative AI for CS1 Code Grading: Direct vs Reverse Methods

• URL: http://arxiv.org/abs/2511.14798v1
• Date: Mon, 17 Nov 2025 01:38:06 GMT
• Title: Evaluating Generative AI for CS1 Code Grading: Direct vs Reverse Methods
• Authors: Ahmad Memon, Abdallah Mohamed,
• Abstract summary: This paper compares two AI-based grading techniques: textitDirect, where the AI model applies a rubric directly to student code, and textitReverse (a newly proposed approach), where the AI first fixes errors, then deduces a grade based on the nature and number of fixes.<n>We discuss the strengths and limitations of each approach, practical considerations for prompt design, and future directions for hybrid human-AI grading systems.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Manual grading of programming assignments in introductory computer science courses can be time-consuming and prone to inconsistencies. While unit testing is commonly used for automatic evaluation, it typically follows a binary pass/fail model and does not give partial marks. Recent advances in large language models (LLMs) offer the potential for automated, scalable, and more objective grading. This paper compares two AI-based grading techniques: \textit{Direct}, where the AI model applies a rubric directly to student code, and \textit{Reverse} (a newly proposed approach), where the AI first fixes errors, then deduces a grade based on the nature and number of fixes. Each method was evaluated on both the instructor's original grading scale and a tenfold expanded scale to assess the impact of range on AI grading accuracy. To assess their effectiveness, AI-assigned scores were evaluated against human tutor evaluations on a range of coding problems and error types. Initial findings suggest that while the Direct approach is faster and straightforward, the Reverse technique often provides a more fine-grained assessment by focusing on correction effort. Both methods require careful prompt engineering, particularly for allocating partial credit and handling logic errors. To further test consistency, we also used synthetic student code generated using Gemini Flash 2.0, which allowed us to evaluate AI graders on a wider range of controlled error types and difficulty levels. We discuss the strengths and limitations of each approach, practical considerations for prompt design, and future directions for hybrid human-AI grading systems that aim to improve consistency, efficiency, and fairness in CS courses.

Related papers

• Evaluating AI Grading on Real-World Handwritten College Mathematics: A Large-Scale Study Toward a Benchmark [9.922581736690159]
  We present a large-scale empirical study of AI grading on real, handwritten calculus work from UC Irvine.<n>Using OCR-conditioned large language models with structured, rubric-guided prompting, our system produces scores and formative feedback for thousands of free-response quiz submissions.<n>In a setting with no single ground-truth label, we evaluate performance against official teaching-assistant grades, student surveys, and independent human review.
  arXiv  Detail & Related papers  (2026-03-01T03:32:51Z)
• Beyond Static Scoring: Enhancing Assessment Validity via AI-Generated Interactive Verification [0.4260312058817663]
  Large Language Models (LLMs) challenge the validity of traditional open-ended assessments by blurring the lines of authorship.<n>This paper introduces a novel Human-AI Collaboration framework that enhances assessment integrity by combining rubric-based automated scoring with AI-generated, targeted follow-up questions.
  arXiv  Detail & Related papers  (2025-12-14T08:13:53Z)
• From Coders to Critics: Empowering Students through Peer Assessment in the Age of AI Copilots [3.3094795918443634]
  This paper presents an empirical study of a rubric based, anonymized peer review process implemented in a large programming course.<n>Students evaluated each other's final projects (2D game) and their assessments were compared to instructor grades using correlation, mean absolute error, and root mean square error (RMSE)<n>Results show that peer review can approximate instructor evaluation with moderate accuracy and foster student engagement, evaluative thinking, and interest in providing good feedback to their peers.
  arXiv  Detail & Related papers  (2025-05-28T08:17:05Z)
• The Failure of Plagiarism Detection in Competitive Programming [0.0]
  Plagiarism in programming courses remains a persistent challenge.<n>This paper examines why traditional code plagiarism detection methods frequently fail in competitive programming contexts.<n>We find that widely-used automated similarity checkers can be thwarted by simple code transformations or novel AI-generated code.
  arXiv  Detail & Related papers  (2025-05-13T05:43:49Z)
• Subtle Errors in Reasoning: Preference Learning via Error-injected Self-editing [59.405145971637204]
  We propose a novel preference learning framework called eRror-Injected Self-Editing (RISE)<n>RISE injects predefined subtle errors into pivotal tokens in reasoning or steps to construct hard pairs for error mitigation.<n>Experiments validate the effectiveness of RISE, with preference learning on Qwen2-7B-Instruct yielding notable improvements of 3.0% on GSM8K and 7.9% on MATH with only 4.5K training samples.
  arXiv  Detail & Related papers  (2024-10-09T07:43:38Z)
• Evaluating Mathematical Reasoning Beyond Accuracy [50.09931172314218]
  We introduce ReasonEval, a new methodology for evaluating the quality of reasoning steps.<n>We show that ReasonEval consistently outperforms baseline methods in the meta-evaluation datasets.<n>We observe that ReasonEval can play a significant role in data selection.
  arXiv  Detail & Related papers  (2024-04-08T17:18:04Z)
• Beyond Static Evaluation: A Dynamic Approach to Assessing AI Assistants' API Invocation Capabilities [48.922660354417204]
  We propose Automated Dynamic Evaluation (AutoDE) to assess an assistant's API call capability without human involvement. In our framework, we endeavor to closely mirror genuine human conversation patterns in human-machine interactions.
  arXiv  Detail & Related papers  (2024-03-17T07:34:12Z)
• Automating the Correctness Assessment of AI-generated Code for Security Contexts [8.009107843106108]
  We propose a fully automated method, named ACCA, to evaluate the correctness of AI-generated code for security purposes. We use ACCA to assess four state-of-the-art models trained to generate security-oriented assembly code. Our experiments show that our method outperforms the baseline solutions and assesses the correctness of the AI-generated code similar to the human-based evaluation.
  arXiv  Detail & Related papers  (2023-10-28T22:28:32Z)
• A Comparative Study of Filters and Deep Learning Models to predict Diabetic Retinopathy [0.0]
  This study compares the outcomes of various deep learning models, including InceptionNetV3, utilizing a variety of image filters. The objective is to improve the diagnostic processes for Diabetic Retinopathy (DR), the primary cause of diabetes-related blindness.
  arXiv  Detail & Related papers  (2023-09-26T19:21:09Z)
• Prior Knowledge Guided Unsupervised Domain Adaptation [82.9977759320565]
  We propose a Knowledge-guided Unsupervised Domain Adaptation (KUDA) setting where prior knowledge about the target class distribution is available. In particular, we consider two specific types of prior knowledge about the class distribution in the target domain: Unary Bound and Binary Relationship. We propose a rectification module that uses such prior knowledge to refine model generated pseudo labels.
  arXiv  Detail & Related papers  (2022-07-18T18:41:36Z)
• ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback [54.142719510638614]
  In this paper, we frame the problem of providing feedback as few-shot classification. A meta-learner adapts to give feedback to student code on a new programming question from just a few examples by instructors. Our approach was successfully deployed to deliver feedback to 16,000 student exam-solutions in a programming course offered by a tier 1 university.
  arXiv  Detail & Related papers  (2021-07-23T22:41:28Z)
• Hierarchical Bi-Directional Self-Attention Networks for Paper Review Rating Recommendation [81.55533657694016]
  We propose a Hierarchical bi-directional self-attention Network framework (HabNet) for paper review rating prediction and recommendation. Specifically, we leverage the hierarchical structure of the paper reviews with three levels of encoders: sentence encoder (level one), intra-review encoder (level two) and inter-review encoder (level three) We are able to identify useful predictors to make the final acceptance decision, as well as to help discover the inconsistency between numerical review ratings and text sentiment conveyed by reviewers.
  arXiv  Detail & Related papers  (2020-11-02T08:07:50Z)
• Evaluation Toolkit For Robustness Testing Of Automatic Essay Scoring Systems [64.4896118325552]
  We evaluate the current state-of-the-art AES models using a model adversarial evaluation scheme and associated metrics. We find that AES models are highly overstable. Even heavy modifications(as much as 25%) with content unrelated to the topic of the questions do not decrease the score produced by the models.
  arXiv  Detail & Related papers  (2020-07-14T03:49:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.