🏷️ human-in-the-loop-ai

> **Synthesis:** Li (2026) presents a conceptual Perspective arguing that AI-assisted vocal pedagogy should be evaluated not by how precisely AI measures vocal output (pitch, stability, timing) but by…

2026-08-13 · generative-ai, feedback-loop, self-regulated-learning, metacognition, music-education

> **Hallucination Risk** — the danger that AI systems generate plausible but factually incorrect or fabricated content in educational contexts, where such errors can mislead learners, undermine trust,…

2026-08-09 · hallucination-risk, ai-ed-evaluation, generative-ai, llm, pedagogical-safety

A conceptual/position paper arguing that feedback in an age of GenAI must be understood as **"matters of care"** — ethical, relational practices rather than information transmission. It builds on a te…

2026-08-03 · generative-ai, feedback-loop, higher-ed, educational-theory, equity

This editorial synthesises the seven papers of the AEHE 51(5) special issue on feedback in the age of generative AI. Its central claim: the question is **not whether GenAI feedback is useful, but how …

2026-08-03 · generative-ai, feedback-loop, higher-ed, ai-literacy, educational-theory

An empirical study of **21 higher-education teachers** using **PolyFeed**, an AI-powered feedback tool combining (1) a **BERT-based ML model** (from Aldino et al. 2024) that detects which learner-cent…

2026-08-03 · generative-ai, feedback-loop, teacher-role, higher-ed, faculty-development

> **AICoFE** (AI-based Collaborative Feedback) is a multi-LLM feedback generation system for higher education that combines independently fine-tuned language models with **teacher-in-the-loop mediatio…

2026-07-29 · ai-ed-evaluation, feedback-loop, student-experience, higher-ed, learning-analytics

MindCopilot introduces a formal framework for evaluating human-LLM co-writing that shifts from output-only metrics (BLEU, ROUGE) to **interaction-aware evaluation**. The paper models co-writing as a *…

2026-05-25 · feedback-loop, higher-ed, human-in-the-loop, llm, writing-education

RAG-based rubric-grounded GenAI writing feedback improved student revision quality (N=143, grades 7-11) and saved teacher time, but automated ratings were inconsistent. CyberScholar demonstrates rubri…

2026-05-19 · generative-ai, llm, writing-education, k-12, formative-assessment

Socratic questioning, reflection prompts, misconception checks, and mandatory pauses produce better K-12 engagement than directive answer-giving AI tutors. SocratiCode demonstrates a participatory des…

2026-05-19 · intelligent-tutoring, llm, generative-ai, k-12, scaffolding

> Are Agents Ready to Teach? A Multi-Stage Benchmark for Real-World Teaching Workflows **Chen et al. (2026)** — Multiple institutions. Under review.…

2026-05-15 · agentic-ai, benchmark, generative-ai, intelligent-tutoring, llm

> Understanding How International Students in the U.S. Are Using Conversational AI to Support Cross-Cultural Adaptation **Nourian et al. (2026)** — Multiple institutions. arXiv cs.HC.…

2026-05-15 · higher-ed, student-experience, generative-ai, llm, equity

AICoFe orchestrates a multi-LLM pipeline using GPT-4.1-mini, Gemini 2.5 Flash, and Llama 3.1 to synthesize quantitative rubric data and qualitative observations into actionable feedback for higher edu…

2026-05-14 · automated-grading, feedback-loop, higher-ed, llm, learning-analytics

> Stop treating κ > 0.8 as a binary stamp of approval.…

2026-05-11 · benchmark, efficacy-study, learning-analytics, generative-ai, llm

**AI multimodal feedback matches educator feedback for learning while significantly outperforming it on student perceptions.** The authors built a real-time AI-facilitated multimodal feedback system i…

2026-05-11 · multimodal, feedback-loop, generative-ai, llm, student-experience

**Sequenced AI feedback harms learning despite boosting engagement and positive perceptions.** In a randomized experiment with 199 participants, the authors compared two types of AI-generated feedback…

2026-05-11 · feedback-loop, formative-assessment, scaffolding, generative-ai, efficacy-study

> A set of 19 empirically-grounded design guidelines for AI-supported learning technologies tailored to adult learners, synthesized by Reddig et al. (2026) from longitudinal deployment data at a US na…

2026-05-09 · lifelong-learning, personalized-learning, adaptive-learning, faculty-development, edtech-platform

> A web-based system that uses LLMs and Learning Analytics dashboards to provide automated, rubric-based feedback on student presentation slides. Developed by Becerra et al. (2026), AISSA addresses th…

2026-05-09 · automated-grading, learning-analytics, formative-assessment, higher-ed, llm

> A bibliometric–systematic review of AI tools in STEM education: > Systematic review (2005–2025) mapping how AI tools scaffold and co-regulate metacognitive development in STEM classrooms through bib…

2026-05-08 · metacognition, stem-education, learning-analytics, intelligent-tutoring, posthumanist

> Embedding the Knowledge–Learning–Instruction (KLI) framework into multi-agent systems to act as sophisticated instructional designers for K-12 educators.…

2026-05-08 · agentic-ai, ai-literacy, human-in-the-loop, k-12, pedagogical-safety

> Schleifer, Ariely & Klebanov (2026) investigate a critical gap in [[automated-grading]]: **how scoring quality degrades for mid-range student responses**. Most ASAS evaluations focus on clearly corr…

2026-05-08 · automated-grading, formative-assessment, llm, benchmark, efficacy-study

> **MuTSE** (Roscan et al., 2026) addresses a critical need in **Intelligent Tutoring Systems (ITS)**: delivering content at the right reading level for each learner. > Human-in-the-loop evaluation fr…

2026-05-08 · intelligent-tutoring, nlp-education, adaptive-learning, human-in-the-loop, generative-ai

> A design framework for educational AI systems structured around four agentic paradigms: **reflection**, **planning**, **tool use**, and **multi-agent collaboration**. Proposed by Kamalov et al. (202…

2026-05-07 · agentic-ai, ai-education, benchmark, intelligent-tutoring, pedagogical-llm-training

> Zerkouk, Mihoubi & Chikhaoui (2025) systematically analyzed qualified studies from 2010–2025 across: > A comprehensive systematic review of AI-based Intelligent Tutoring Systems (2010–2025) reveals …

2026-05-07 · intelligent-tutoring, benchmark, efficacy-study, higher-ed, k-12

> Wiggins (1990) proposed AA as a counterbalance to standardised tests: direct examination of "student performance on worthy intellectual tasks." > Authentic assessment (AA) has evolved from workplace…

2026-05-07 · ai-ed-evaluation, ai-education, assessment, formative-assessment, higher-ed

> Automatic Short Answer Grading (ASAG) is never perfect. Upper bounds on accuracy arise from: > Zero-shot LLMs perform strongly on ASAG without task-specific fine-tuning, but **model-based confidence…

2026-05-07 · automated-grading, llm, formative-assessment, feedback-loop, higher-ed

> The framework rests on three interconnected anchors that must be addressed *before* selecting tools: > Rejecting the binary promise-vs-peril discourse and the rush to immediate implementation, Finke…

2026-05-07 · ai-education, higher-ed, pedagogy, scaffolding, policy-maker

> Bannò, Knill & Gales (2026) propose a paradigm shift in automated essay scoring: from **inter-learner ranking** to **intra-learner profiling**. Instead of asking "how does this essay rank against ot…

2026-05-05 · automated-grading, writing-education, llm, ai-education, higher-ed