CS-Guide: Leveraging LLMs and Student Reflections to Provide Frequent, Scalable Academic Monitoring Feedback to Computer Science Students

• URL: http://arxiv.org/abs/2512.19866v1
• Date: Mon, 22 Dec 2025 20:43:59 GMT
• Title: CS-Guide: Leveraging LLMs and Student Reflections to Provide Frequent, Scalable Academic Monitoring Feedback to Computer Science Students
• Authors: Samuel Jacob Chacko, An-I Andy Wang, Lara Perez-Felkner, Sonia Haiduc, David Whalley, Xiuwen Liu,
• Abstract summary: CS departments often serve large student populations, making timely academic monitoring and personalized feedback difficult.<n>We present CS-Guide, which leverages Large Language Models (LLMs) to deliver scalable, frequent academic feedback.<n>We evaluated CS-Guide on a four-year, 20K-entry longitudinal dataset, and it achieved up to a 97% F1 score in recommending interventions for first-year students.
• Score: 2.2012643583422347
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Computer Science (CS) departments often serve large student populations, making timely academic monitoring and personalized feedback difficult. While the recommended counselor-to-student ratio is 250:1, it often exceeds 350:1 in practice, leading to delays in support and interventions. We present CS-Guide, which leverages Large Language Models (LLMs) to deliver scalable, frequent academic feedback. Weekly, students interact with CS-Guide through self-reported grades and reflective journal entries, from which CS-Guide extracts quantitative and qualitative features and triggers tailored interventions (e.g., academic support, health and wellness referrals). Thus, CS-Guide uniquely integrates learning analytics, LLMs, and actionable interventions using both structured and unstructured student-generated data. We evaluated CS-Guide on a four-year, ~20K-entry longitudinal dataset, and it achieved up to a 97% F1 score in recommending interventions for first-year students. This shows that CS-Guide can enhance advising systems with scalable, consistent, timely, and domain-specific feedback.

Related papers

• ResearchGPT: Benchmarking and Training LLMs for End-to-End Computer Science Research Workflows [109.34792911044394]
  CS-54k is a high-quality corpus of scientific Q&A pairs in computer science.<n> CS-4k is a benchmark for evaluating AI's ability to assist scientific research.<n> CS-50k is a large-scale training dataset.
  arXiv  Detail & Related papers  (2025-10-23T07:07:35Z)
• Investigating Student Interaction Patterns with Large Language Model-Powered Course Assistants in Computer Science Courses [4.761218834684297]
  Large language models (LLMs) are promising for bridging this gap, but interactions between students and LLMs are rarely overseen by educators.<n>We developed and studied an LLM-powered course assistant deployed across multiple computer science courses to characterize real-world use and understand pedagogical implications.
  arXiv  Detail & Related papers  (2025-09-10T02:21:11Z)
• LecEval: An Automated Metric for Multimodal Knowledge Acquisition in Multimedia Learning [58.98865450345401]
  We introduce LecEval, an automated metric grounded in Mayer's Cognitive Theory of Multimedia Learning.<n>LecEval assesses effectiveness using four rubrics: Content Relevance (CR), Expressive Clarity (EC), Logical Structure (LS) and Audience Engagement (AE)<n>We curate a large-scale dataset of over 2,000 slides from more than 50 online course videos, annotated with fine-grained human ratings.
  arXiv  Detail & Related papers  (2025-05-04T12:06:47Z)
• Managing Project Teams in an Online Class of 1000+ Students [19.36506075950085]
  Team projects in Computer Science (CS) help students build collaboration skills, apply theory, and prepare for real-world software development.<n>Online classes present unique opportunities to transform the accessibility of CS education at scale.<n>We discuss our approach of managing, evaluating, and providing constructive feedback to over 200 project teams.
  arXiv  Detail & Related papers  (2024-12-15T04:16:32Z)
• A Large-Scale Study of Relevance Assessments with Large Language Models: An Initial Look [52.114284476700874]
  This paper reports on the results of a large-scale evaluation (the TREC 2024 RAG Track) where four different relevance assessment approaches were deployed. We find that automatically generated UMBRELA judgments can replace fully manual judgments to accurately capture run-level effectiveness. Surprisingly, we find that LLM assistance does not appear to increase correlation with fully manual assessments, suggesting that costs associated with human-in-the-loop processes do not bring obvious tangible benefits.
  arXiv  Detail & Related papers  (2024-11-13T01:12:35Z)
• The Crowd in MOOCs: A Study of Learning Patterns at Scale [38.0172611348248]
  We analyze a dataset of 351 million learning activities from 0.8 million unique learners enrolled in over 1.6 thousand courses within two years. We find that the time intervals between consecutive learning activities of learners exhibit a mix of power-law and periodic cosine function distribution. We demonstrate these findings can facilitate manifold applications including recommendation tasks on courses.
  arXiv  Detail & Related papers  (2024-08-06T08:16:26Z)
• End-to-end Learnable Clustering for Intent Learning in Recommendation [54.157784572994316]
  We propose a novel intent learning method termed underlineELCRec. It unifies behavior representation learning into an underlineEnd-to-end underlineLearnable underlineClustering framework. We deploy this method on the industrial recommendation system with 130 million page views and achieve promising results.
  arXiv  Detail & Related papers  (2024-01-11T15:22:55Z)
• 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)
• Learning Action Conditions from Instructional Manuals for Instruction Understanding [48.52663250368341]
  We propose a task dubbed action condition inference, and collecting a high-quality, human annotated dataset of preconditions and postconditions of actions in instructional manuals. We propose a weakly supervised approach to automatically construct large-scale training instances from online instructional manuals, and curate a densely human-annotated and validated dataset to study how well the current NLP models can infer action-condition dependencies in instruction texts.
  arXiv  Detail & Related papers  (2022-05-25T00:19:59Z)
• Insights for post-pandemic pedagogy across one CS department [1.1756822700775666]
  We studied one computer science department that serves residential and remote undergraduate and graduate students. We conducted interviews with stakeholders in the department and ran a department-wide student survey. Our case study outlines what the instructors did, summarizes what instructors and students say about courses during this period.
  arXiv  Detail & Related papers  (2022-03-17T03:14:52Z)
• Self-Supervised Reinforcement Learning for Recommender Systems [77.38665506495553]
  We propose self-supervised reinforcement learning for sequential recommendation tasks. Our approach augments standard recommendation models with two output layers: one for self-supervised learning and the other for RL. Based on such an approach, we propose two frameworks namely Self-Supervised Q-learning(SQN) and Self-Supervised Actor-Critic(SAC)
  arXiv  Detail & Related papers  (2020-06-10T11:18:57Z)

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.