LLM Contribution Summarization in Software Projects

• URL: http://arxiv.org/abs/2505.17710v1
• Date: Fri, 23 May 2025 10:26:43 GMT
• Title: LLM Contribution Summarization in Software Projects
• Authors: Rafael Corsi Ferrao, Fabio Roberto de Miranda, Diego Pavan Soler,
• Abstract summary: This paper addresses the need for an automated and objective approach to evaluate individual contributions within team projects.<n>We present a tool that leverages a large language model (LLM) to automatically summarize code contributions extracted from version control repositories.<n>The tool was assessed over two semesters during a three-week, full-time software development sprint involving 65 students.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This full paper in innovative practice provides an automated tool to summarize individual code contributions in project-based courses with external clients. Real industry projects offer valuable learning opportunities by immersing students in authentic problems defined by external clients. However, the open-ended and highly variable scope of these projects makes it challenging for instructors and teaching assistants to provide timely and detailed feedback. This paper addresses the need for an automated and objective approach to evaluate individual contributions within team projects. In this paper, we present a tool that leverages a large language model (LLM) to automatically summarize code contributions extracted from version control repositories. The tool preprocesses and structures repository data, and uses PyDriller to isolate individual contributions. Its uniqueness lies in the combination of LLM prompt engineering with automated repository analysis, thus reducing the manual grading burden while providing regular and informative updates. The tool was assessed over two semesters during a three-week, full-time software development sprint involving 65 students. Weekly summaries were provided to teams, and both student and faculty feedback indicated the tool's overall usefulness in informing grading and guidance. The tool reports, in large proportion, activities that were in fact performed by the student, with some failure to detect students' contribution. The summaries were considered by the instructors as a useful potential tool to keep up with the projects.

Related papers

• The Lazy Student's Dream: ChatGPT Passing an Engineering Course on Its Own [3.2334676138718677]
  This paper presents a comprehensive investigation into the capability of Large Language Models (LLMs) to successfully complete a control systems course.<n>We assess LLM performance using ChatGPT under a "minimal effort" protocol that simulates realistic student usage patterns.<n>Our analysis provides quantitative insights into AI's strengths and limitations in handling mathematical formulations, coding challenges, and theoretical concepts in control systems engineering.
  arXiv  Detail & Related papers  (2025-02-23T18:47:14Z)
• Learning to Ask: When LLM Agents Meet Unclear Instruction [55.65312637965779]
  Large language models (LLMs) can leverage external tools for addressing a range of tasks unattainable through language skills alone.<n>We evaluate the performance of LLMs tool-use under imperfect instructions, analyze the error patterns, and build a challenging tool-use benchmark called Noisy ToolBench.<n>We propose a novel framework, Ask-when-Needed (AwN), which prompts LLMs to ask questions to users whenever they encounter obstacles due to unclear instructions.
  arXiv  Detail & Related papers  (2024-08-31T23:06:12Z)
• Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agents [56.822238860147024]
  Augmenting large language models with external tools has emerged as a promising approach to extend their utility.<n>Previous methods manually parse tool documentation and create in-context demonstrations, transforming tools into structured formats for LLMs to use in their step-by-step reasoning.<n>We propose AutoTools, a framework that enables LLMs to automate the tool-use workflow.
  arXiv  Detail & Related papers  (2024-05-26T11:40:58Z)
• Towards Completeness-Oriented Tool Retrieval for Large Language Models [60.733557487886635]
  Real-world systems often incorporate a wide array of tools, making it impractical to input all tools into Large Language Models. Existing tool retrieval methods primarily focus on semantic matching between user queries and tool descriptions. We propose a novel modelagnostic COllaborative Learning-based Tool Retrieval approach, COLT, which captures not only the semantic similarities between user queries and tool descriptions but also takes into account the collaborative information of tools.
  arXiv  Detail & Related papers  (2024-05-25T06:41:23Z)
• Automated User Story Generation with Test Case Specification Using Large Language Model [0.0]
  We developed a tool "GeneUS" to automatically create user stories from requirements documents. The output is provided in format leaving the possibilities open for downstream integration to the popular project management tools.
  arXiv  Detail & Related papers  (2024-04-02T01:45:57Z)
• Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios [93.68764280953624]
  UltraTool is a novel benchmark designed to improve and evaluate Large Language Models' ability in tool utilization. It emphasizes real-world complexities, demanding accurate, multi-step planning for effective problem-solving. A key feature of UltraTool is its independent evaluation of planning with natural language, which happens before tool usage.
  arXiv  Detail & Related papers  (2024-01-30T16:52:56Z)
• CLOVA: A Closed-Loop Visual Assistant with Tool Usage and Update [69.59482029810198]
  CLOVA is a Closed-Loop Visual Assistant that operates within a framework encompassing inference, reflection, and learning phases. Results demonstrate that CLOVA surpasses existing tool-usage methods by 5% in visual question answering and multiple-image reasoning, by 10% in knowledge tagging, and by 20% in image editing.
  arXiv  Detail & Related papers  (2023-12-18T03:34:07Z)
• TaskBench: Benchmarking Large Language Models for Task Automation [82.2932794189585]
  We introduce TaskBench, a framework to evaluate the capability of large language models (LLMs) in task automation. Specifically, task decomposition, tool selection, and parameter prediction are assessed. Our approach combines automated construction with rigorous human verification, ensuring high consistency with human evaluation.
  arXiv  Detail & Related papers  (2023-11-30T18:02:44Z)
• Patterns of Student Help-Seeking When Using a Large Language Model-Powered Programming Assistant [2.5949084781328744]
  This study examines students' use of an innovative tool that provides on-demand programming assistance without revealing solutions directly. We collected more than 2,500 queries submitted by students throughout the term. We found that most queries requested immediate help with programming assignments, whereas fewer requests asked for help on related concepts or for deepening conceptual understanding.
  arXiv  Detail & Related papers  (2023-10-25T20:36:05Z)
• Automated grading workflows for providing personalized feedback to open-ended data science assignments [1.534667887016089]
  In this paper, we discuss the steps of a typical grading workflow and highlight which steps can be automated in an approach that we call automated grading workflow. We illustrate how gradetools, a new R package, implements this approach within RStudio to facilitate efficient and consistent grading while providing individualized feedback.
  arXiv  Detail & Related papers  (2023-08-18T01:22:11Z)
• CodeHelp: Using Large Language Models with Guardrails for Scalable Support in Programming Classes [2.5949084781328744]
  Large language models (LLMs) have emerged recently and show great promise for providing on-demand help at a large scale. We introduce CodeHelp, a novel LLM-powered tool designed with guardrails to provide on-demand assistance to programming students without directly revealing solutions. Our findings suggest that CodeHelp is well-received by students who especially value its availability and help with resolving errors, and that for instructors it is easy to deploy and complements, rather than replaces, the support that they provide to students.
  arXiv  Detail & Related papers  (2023-08-14T03:52:24Z)
• 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)

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.