AICoFe: Implementation and Deployment of an AI-Based Collaborative Feedback System for Higher Education

• URL: http://arxiv.org/abs/2605.04740v1
• Date: Wed, 06 May 2026 10:37:32 GMT
• Title: AICoFe: Implementation and Deployment of an AI-Based Collaborative Feedback System for Higher Education
• Abstract summary: AICoFe (AI-based Collaborative Feedback) is a system designed to bridge this gap through a human-centered AI approach.<n>We describe a modular architecture that orchestrates a multi-LLM pipeline, utilizing GPT-4.1-mini, Gemini 2.5 Flash, and Llama 3.1, to synthesize quantitative data and qualitative observations into coherent, actionable feedback.<n>Key to the system is a "teacher-in-the-loop" mediation workflow, where educators use specialized Learning Analytics dashboards to curate and refine AI-generated drafts.
• Score: 41.99844472131922
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Effective peer feedback is essential for developing critical reflection in higher education, yet its impact is often limited by the inconsistent quality of student-generated comments. This paper presents the implementation and deployment of AICoFe (AI-based Collaborative Feedback), a system designed to bridge this gap through a human-centered AI approach. We describe a modular architecture that orchestrates a multi-LLM pipeline, utilizing GPT-4.1-mini, Gemini 2.5 Flash, and Llama 3.1, to synthesize quantitative rubric data and qualitative observations into coherent, actionable feedback. Key to the system is a "teacher-in-the-loop" mediation workflow, where educators use specialized Learning Analytics dashboards to curate and refine AI-generated drafts before delivery. Furthermore, we detail the underlying data infrastructure, which employs a hybrid SQL and MongoDB strategy to ensure traceability and manage semi-structured feedback versions.

Related papers

• PsyScore: A Psychometrically-Aware Framework for Trait-Adaptive Essay Scoring and ZPD-Scaffolded Feedback [13.817126458402017]
  PsyScore is a psychometrically-aware framework that integrates diagnostic assessment with instructional scaffolding through a shared latent ability representation.<n> Experiments on the ASAP++ dataset demonstrate that PsyScore achieves competitive scoring performance while providing more pedagogically aligned feedback.
  arXiv  Detail & Related papers  (2026-06-18T14:29:13Z)
• Design Principles and Observable Indicators for AI-Enabled Pedagogical Accompaniment: Evidence from the Amico Dual-Mode Prototype in Italy and China [0.0]
  This paper proposes a framework for AI-enabled pedagogical accompaniment, grounded in a human-in-command approach.<n>Building on the Amico project, we operationalize the concept of a relational bridge as a sequence of micro-mediations.<n>The paper outlines an initial cross-context exploration of the prototype in Italy and China and discusses how the two interaction modes, AmicoMio and AmicoTuo, can be used.
  arXiv  Detail & Related papers  (2026-05-20T03:32:07Z)
• UniDial-EvalKit: A Unified Toolkit for Evaluating Multi-Faceted Conversational Abilities [70.79422099851506]
  We present UniDial-EvalKit (UDE), a unified evaluation toolkit for assessing interactive AI systems.<n>UDE standardizes heterogeneous data formats into a universal schema, streamlines complex evaluation pipelines through a modular architecture, and aligns metric calculations under a consistent scoring interface.
  arXiv  Detail & Related papers  (2026-03-24T13:01:31Z)
• Sandpiper: Orchestrated AI-Annotation for Educational Discourse at Scale [3.0317183198617066]
  We present Sandpiper, a mixed-initiative system designed to serve as a bridge between high-volume conversational data and human qualitative expertise.<n>We propose a user study to evaluate the system's efficacy in improving research efficiency, inter-rater reliability, and researcher trust in AI-assisted qualitative analysis.
  arXiv  Detail & Related papers  (2026-03-09T14:01:42Z)
• TAMUSA-Chat: A Domain-Adapted Large Language Model Conversational System for Research and Responsible Deployment [0.0]
  TAMUSA-Chat is a framework for building domain-adapted large language model conversational systems.<n>We show how academic institutions can develop contextually grounded conversational agents while maintaining transparency, governance compliance, and responsible AI practices.
  arXiv  Detail & Related papers  (2026-02-14T04:44:52Z)
• Beyond Holistic Scores: Automatic Trait-Based Quality Scoring of Argumentative Essays [15.895792302323883]
  In educational contexts, teachers and learners require interpretable, trait-level feedback.<n>We study trait-based Automatic Argumentative Essay Scoring using two complementary modeling paradigms.<n>We show that explicitly modeling score ordinality substantially improves agreement with human raters.
  arXiv  Detail & Related papers  (2026-02-04T14:30:52Z)
• Teaching at Scale: Leveraging AI to Evaluate and Elevate Engineering Education [3.557803321422781]
  This article presents a scalable, AI-supported framework for qualitative student feedback using large language models.<n>The system employs hierarchical summarization, anonymization, and exception handling to extract actionable themes from open-ended comments.<n>We report on its successful deployment across a large college of engineering.
  arXiv  Detail & Related papers  (2025-08-01T20:27:40Z)
• MOSAIC-F: A Framework for Enhancing Students' Oral Presentation Skills through Personalized Feedback [1.0835264351334324]
  This framework integrates Multimodal Learning Analytics (MMLA), Observations, Sensors, Artificial Intelligence (AI), and Collaborative assessments.<n>By combining human-based and data-based evaluation techniques, this framework enables more accurate, personalized and actionable feedback.
  arXiv  Detail & Related papers  (2025-06-10T09:46:31Z)
• On the Role of Feedback in Test-Time Scaling of Agentic AI Workflows [71.92083784393418]
  Agentic AI (systems that autonomously plan and act) are becoming widespread, yet their task success rate on complex tasks remains low.<n>Inference-time alignment relies on three components: sampling, evaluation, and feedback.<n>We introduce Iterative Agent Decoding (IAD), a procedure that repeatedly inserts feedback extracted from different forms of critiques.
  arXiv  Detail & Related papers  (2025-04-02T17:40:47Z)
• Hierarchical and Decoupled BEV Perception Learning Framework for Autonomous Driving [52.808273563372126]
  This paper proposes a novel hierarchical BEV perception paradigm, aiming to provide a library of fundamental perception modules and user-friendly graphical interface. We conduct the Pretrain-Finetune strategy to effectively utilize large scale public datasets and streamline development processes. We also present a Multi-Module Learning (MML) approach, enhancing performance through synergistic and iterative training of multiple models.
  arXiv  Detail & Related papers  (2024-07-17T11:17:20Z)
• System-Level Natural Language Feedback [83.24259100437965]
  We show how to use feedback to formalize system-level design decisions in a human-in-the-loop-process. We conduct two case studies of this approach for improving search query and dialog response generation. We show the combination of system-level and instance-level feedback brings further gains.
  arXiv  Detail & Related papers  (2023-06-23T16:21:40Z)
• Edge-assisted Democratized Learning Towards Federated Analytics [67.44078999945722]
  We show the hierarchical learning structure of the proposed edge-assisted democratized learning mechanism, namely Edge-DemLearn. We also validate Edge-DemLearn as a flexible model training mechanism to build a distributed control and aggregation methodology in regions.
  arXiv  Detail & Related papers  (2020-12-01T11:46:03Z)

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.