Teacher Support Tools

FACET is a teacher-facing LLM-based multi-agent system that generates personalized mathematics worksheets for grade 8 students by modeling learner profiles (cognitive proficiency and intrinsic motivation), adapting content through a teacher agent, and evaluating quality through an automated evaluator agent. The system was evaluated through automated agent-based assessment and exploratory feedback from K-12 in-service teachers on authentic curriculum content.

This paper evaluates three multi-agent LLM systems that embed the Knowledge-Learning-Instruction (KLI) framework to generate secondary Math and Science learning activities, comparing them against a baseline single-agent system through teacher evaluations and LLM-as-a-judge assessments using Quality Matters K-12 standards. The study demonstrates that collaborative multi-agent systems can produce more pedagogically sound, creative, and classroom-ready activities by encoding learning science principles directly into the AI architecture.

This paper presents a co-design pilot study with 19 K-12 teachers examining the classroom implementation of an AI-powered grading platform (Colleague AI) that generates rubrics and provides automated feedback on student work. Through usage logs, surveys, and interviews, the study evaluates teacher and student perspectives on AI-generated scoring versus narrative feedback, revealing trust issues with automated grading but appreciation for rapid formative feedback.

EduBench introduces a comprehensive benchmark dataset with 18,821 data points across 9 educational scenarios and 4,000+ educational contexts (covering K-12 and higher education subjects, different difficulty levels, and multiple question types), evaluated using 12 multi-dimensional metrics covering scenario adaptation, factual/reasoning accuracy, and pedagogical application. The benchmark assesses LLM capabilities in diverse educational tasks including assignment grading, study planning, tutoring, and psychological counseling, with both human and automated evaluation.

This paper introduces PBLBench, a benchmark for evaluating multimodal large language models (MLLMs) on their ability to assess STEM Project-Based Learning (PBL) outcomes, including evaluating research reports, code, experimental data, and videos using expert-validated criteria derived through the Analytic Hierarchy Process (AHP). The benchmark tests 15 MLLMs on grading and ranking PBL projects across multiple STEM disciplines with long-context multimodal inputs.

This systematic review analyzes 30 empirical studies (2021-2024) examining how prompt engineering techniques are applied to large language models in K-12 STEM education contexts, identifying common prompting strategies, model types, and evaluation methods used across teaching and learning applications.

This survey paper systematically reviews LLM applications in education from a technology-centric perspective, covering student/teacher assistance, adaptive learning, and commercial tools, while organizing related datasets, benchmarks, and identifying deployment challenges. It provides a comprehensive taxonomy of how LLMs are being applied across multiple educational contexts including tutoring, assessment, content generation, and personalized learning.

This survey paper comprehensively reviews LLM agents for education, proposing a task-centric taxonomy that categorizes agents based on teaching assistance (classroom simulation, feedback generation, curriculum design) and student support (adaptive learning, knowledge tracing, error correction). The paper analyzes architectures, datasets, benchmarks, and deployment challenges including ethics, hallucination, and overreliance.

This paper introduces The Pedagogy Benchmark, a novel dataset of 920 multiple-choice questions from Chilean teacher training exams designed to evaluate large language models' cross-domain pedagogical knowledge (CDPK) and special education needs (SEND) knowledge. The benchmark tests 97 models on their understanding of teaching strategies, assessment methods, and pedagogical concepts, with accuracies ranging from 28% to 89%.

This paper evaluates the use of pre-trained language models to automatically assess high-inference teaching practices in K-12 math classrooms and simulated teacher training settings, comparing NLP-based measurements against traditional human expert ratings across multiple dimensions of instruction quality including practices for students with special needs.

EduPlanner is an LLM-based multi-agent system that automatically generates and iteratively optimizes instructional designs (lesson plans) for mathematics curriculum, using a Skill-Tree structure to model student knowledge levels and a five-dimensional evaluation framework (CIDDP) to assess lesson plan quality.

This paper presents IDPplanner, a GPT-based tool that assists secondary school teachers in designing interdisciplinary design thinking projects aligned with Singapore's curriculum and 21st-century competencies. A workshop with 33 in-service teachers compared AI-assisted versus manual project planning using a six-dimensional rubric, finding that AI-assisted plans scored higher on curriculum alignment, design thinking application, and coherence.

This study analyzes lesson plans from 29 pre-service elementary teachers who integrated ChatGPT into science learning activities, evaluating their plans using a TPACK-based rubric and examining their perceptions about ChatGPT's pedagogical affordances and risks including student over-dependency. The research identifies how ChatGPT was envisioned for use across science domains and teaching strategies, with teachers expressing both enthusiasm about personalized learning support and concerns about accuracy and cognitive offloading.

This paper evaluates GPT-3.5 and GPT-4 models' ability to automatically assess novice human tutors' use of social-emotional learning strategies during one-on-one middle-school math tutoring sessions, comparing four prompting strategies including RAG. The work aims to enable scalable, automated evaluation of tutor competencies to inform personalized tutor training programs.

This study compares lesson plans created by human curriculum designers versus two GenAI models (fine-tuned LLaMA-2-13b and customized GPT-4) in K-12 mathematics education, evaluating educator preferences across instructional components (warm-up, main task, cool-down) and grade levels. The mixed-methods analysis examines both quantitative preferences and qualitative feedback to identify strengths and limitations of AI-generated lesson plans compared to human-authored ones.

This exploratory self-study examines ChatGPT's capabilities for answering science education questions and generating pedagogical resources like lesson plans, rubrics, and quizzes for K-12 science teachers. The study evaluates ChatGPT's content knowledge, pedagogical outputs, and potential applications in science education while highlighting concerns about epistemic authority and the need for critical evaluation of AI-generated content.

This study evaluates the RADEC (Read-Answer-Discuss-Explain-Create) instructional model integrated with AI tools to enhance science literacy among elementary school pre-service teachers in Indonesia, using student questionnaires to measure understanding of scientific concepts, motivation, problem-solving abilities, and critical thinking skills. The research focuses on preparing future teachers to use AI-enhanced pedagogy rather than directly evaluating AI systems with K-12 students.

This qualitative study investigates programming instructors' perceptions of ChatGPT's potential benefits and drawbacks for computer programming education at a university, exploring how it can support personalized learning, code debugging, and instructional efficiency while raising concerns about over-reliance, accuracy, and ethical issues.

This Indonesian case study examines English language teachers' and learners' perceptions of using AI for literary writing instruction, finding that AI helps with lesson planning, content generation, and writing skill development, but also creates dependency that limits creativity and critical thinking. The research uses questionnaire data to assess both pedagogical benefits and concerns about cognitive offloading.

This paper presents an automated LLM-based pipeline that generates knowledge components (KCs) for programming problems and uses them for knowledge tracing to predict student performance and estimate mastery levels on fine-grained skills. The framework is evaluated on real-world student code submission datasets and compared against human-written KCs and existing knowledge tracing methods.

EduEval is a comprehensive hierarchical benchmark for evaluating LLMs in Chinese K-12 education, comprising 24 task types with over 11,000 questions organized across six cognitive dimensions (Memorization, Understanding, Application, Reasoning, Creativity, and Ethics) based on Bloom's Taxonomy and Webb's Depth of Knowledge. The benchmark uses authentic educational materials including real exam questions, classroom dialogues, student essays, and expert-designed prompts spanning primary through high school levels.

FEANEL is a benchmark for evaluating LLMs' ability to provide fine-grained error analysis and pedagogical feedback on K-12 English writing, comprising 1,000 student essays with expert-annotated errors categorized by type, severity, and explanations. The benchmark specifically assesses whether AI systems can identify writing errors and provide educationally meaningful, interpretable feedback to support student learning.

FACET is a teacher-facing LLM-based multi-agent system that generates personalized mathematics worksheets for grade 8 students by modeling learner profiles (cognitive proficiency and intrinsic motivation), adapting content through a teacher agent, and evaluating quality through an automated evaluator agent. The system was evaluated through automated agent-based assessment and exploratory feedback from K-12 in-service teachers on authentic curriculum content.

This paper evaluates LLM-based and statistical NLP methods for automated scoring of nationwide high school graduation essay exams in Estonia, comparing machine-generated scores against human raters across multiple rubric dimensions including content, argumentation, and language quality. The study demonstrates that automated scoring achieves reliability comparable to human raters while also examining bias, prompt injection risks, and providing personalized feedback capabilities.

This paper evaluates the effectiveness of LLM-generated analogies for teaching scientific concepts (biology and physics) through controlled in-class tests with high school students and classroom field studies with teachers. The study measures student understanding, learning outcomes, potential over-reliance, and teacher satisfaction with LLM-generated analogies, culminating in the development of a practical system for teachers to generate and refine teaching analogies.

This study examines how conversational AI (LLM-based) supports K-12 mathematics educators during lesson preparation by analyzing educator-AI interactions across different educational contexts. The research evaluates AI's ability to adapt responses to educators' instructional needs, assessing accuracy, relevance, and usefulness of AI-generated pedagogical content and guidance.

This paper investigates whether LLMs' generation probabilities and error patterns align with student misconception patterns in multiple-choice questions, using real-world student response data across 3,202 MCQs. The study finds moderate correlation between LLM probabilities and student distractor selections, with LLMs frequently choosing the same incorrect answers that commonly mislead students.

This paper develops and evaluates a ChatGPT-based system that automatically generates personalized reading comprehension exercises (passages and multiple-choice questions) for middle school English learners in China, with extensive human evaluation by students, teachers, and native speakers demonstrating the quality meets or exceeds human-written materials.

This paper evaluates the quality and usefulness of educational questions generated by large language models (specifically GPT-3/InstructGPT) using controllable text generation with Bloom's taxonomy and difficulty levels, validated through teacher assessments across two domains. The study demonstrates that LLM-generated questions are judged by teachers as high quality and sufficiently useful for classroom use.

This paper compares three models (fine-tuned Mistral/GOAT, SBERT-Canberra, and GPT-4) for automatically scoring and providing qualitative feedback on middle-school students' open-ended math responses, evaluating both scoring accuracy and feedback quality using teacher judgments.

EduBench introduces a comprehensive benchmark dataset with 18,821 data points across 9 educational scenarios and 4,000+ educational contexts (covering K-12 and higher education subjects, different difficulty levels, and multiple question types), evaluated using 12 multi-dimensional metrics covering scenario adaptation, factual/reasoning accuracy, and pedagogical application. The benchmark assesses LLM capabilities in diverse educational tasks including assignment grading, study planning, tutoring, and psychological counseling, with both human and automated evaluation.

This empirical study evaluates the impact of Generative AI on elementary school students' writing skills in Indonesian language education, comparing two classes using Generative AI tools against two control classes in terms of completeness, structure, and creativity of written work. Results show significant improvement in writing abilities for students using Generative AI.

This paper introduces PBLBench, a benchmark for evaluating multimodal large language models (MLLMs) on their ability to assess STEM Project-Based Learning (PBL) outcomes, including evaluating research reports, code, experimental data, and videos using expert-validated criteria derived through the Analytic Hierarchy Process (AHP). The benchmark tests 15 MLLMs on grading and ranking PBL projects across multiple STEM disciplines with long-context multimodal inputs.

This paper investigates how assessment construct characteristics (complexity, diversity, structure) affect machine learning model performance when automatically scoring middle school students' written scientific argumentation responses across 17 assessment tasks aligned to K-12 science education standards (NGSS).

This systematic review analyzes 30 empirical studies (2021-2024) examining how prompt engineering techniques are applied to large language models in K-12 STEM education contexts, identifying common prompting strategies, model types, and evaluation methods used across teaching and learning applications.

This paper presents a multi-agent LLM system for automatically generating multiple-choice questions (MCQs) to assess AI literacy in K-12 students (grades 7-9), using critique agents to ensure questions align with learning objectives, grade levels, and Bloom's Taxonomy. Three K-12 AI literacy teaching experts evaluated 40 generated questions using a pedagogical quality rubric.

This paper develops EDUMATH, a system for generating math word problems aligned with K-12 education standards using LLMs, and evaluates over 11,000 generated problems with teacher annotations for solvability, accuracy, educational appropriateness, and standards alignment. The work includes a student study comparing performance and preference between LLM-generated and human-written problems.

This survey paper systematically reviews LLM applications in education from a technology-centric perspective, covering student/teacher assistance, adaptive learning, and commercial tools, while organizing related datasets, benchmarks, and identifying deployment challenges. It provides a comprehensive taxonomy of how LLMs are being applied across multiple educational contexts including tutoring, assessment, content generation, and personalized learning.

This survey paper comprehensively reviews LLM agents for education, proposing a task-centric taxonomy that categorizes agents based on teaching assistance (classroom simulation, feedback generation, curriculum design) and student support (adaptive learning, knowledge tracing, error correction). The paper analyzes architectures, datasets, benchmarks, and deployment challenges including ethics, hallucination, and overreliance.

This paper is a systematic review of large language models (LLMs) used as virtual tutors in education, examining applications including automatic question generation, student assessment, feedback provision, and personalized learning across K-12 and higher education contexts. The review analyzes how LLMs like GPT-3 and BERT are deployed for educational tasks such as generating explanations, grading answers, and providing tutoring support.

EduEval is a comprehensive hierarchical benchmark for evaluating LLMs in Chinese K-12 education, comprising 24 task types with over 11,000 questions organized across six cognitive dimensions (Memorization, Understanding, Application, Reasoning, Creativity, and Ethics) based on Bloom's Taxonomy and Webb's Depth of Knowledge. The benchmark uses authentic educational materials including real exam questions, classroom dialogues, student essays, and expert-designed prompts spanning primary through high school levels.

FACET is a teacher-facing LLM-based multi-agent system that generates personalized mathematics worksheets for grade 8 students by modeling learner profiles (cognitive proficiency and intrinsic motivation), adapting content through a teacher agent, and evaluating quality through an automated evaluator agent. The system was evaluated through automated agent-based assessment and exploratory feedback from K-12 in-service teachers on authentic curriculum content.

This paper evaluates three multi-agent LLM systems that embed the Knowledge-Learning-Instruction (KLI) framework to generate secondary Math and Science learning activities, comparing them against a baseline single-agent system through teacher evaluations and LLM-as-a-judge assessments using Quality Matters K-12 standards. The study demonstrates that collaborative multi-agent systems can produce more pedagogically sound, creative, and classroom-ready activities by encoding learning science principles directly into the AI architecture.

This paper develops and evaluates a ChatGPT-based system that automatically generates personalized reading comprehension exercises (passages and multiple-choice questions) for middle school English learners in China, with extensive human evaluation by students, teachers, and native speakers demonstrating the quality meets or exceeds human-written materials.

EduBench introduces a comprehensive benchmark dataset with 18,821 data points across 9 educational scenarios and 4,000+ educational contexts (covering K-12 and higher education subjects, different difficulty levels, and multiple question types), evaluated using 12 multi-dimensional metrics covering scenario adaptation, factual/reasoning accuracy, and pedagogical application. The benchmark assesses LLM capabilities in diverse educational tasks including assignment grading, study planning, tutoring, and psychological counseling, with both human and automated evaluation.

This paper develops EDUMATH, a system for generating math word problems aligned with K-12 education standards using LLMs, and evaluates over 11,000 generated problems with teacher annotations for solvability, accuracy, educational appropriateness, and standards alignment. The work includes a student study comparing performance and preference between LLM-generated and human-written problems.

This paper develops and evaluates automatic readability assessment models for science education documents in Basque, Spanish, and English for secondary education (ages 12-16), using both machine learning and deep learning approaches to help teachers select appropriately leveled texts for multilingual STEM instruction. The work creates three annotated corpora (BasqueARA, Agrega2Es, Agrega2En+) and tests feature-based and transformer-based models to classify text difficulty levels.

EduPlanner is an LLM-based multi-agent system that automatically generates and iteratively optimizes instructional designs (lesson plans) for mathematics curriculum, using a Skill-Tree structure to model student knowledge levels and a five-dimensional evaluation framework (CIDDP) to assess lesson plan quality.

This paper introduces and evaluates prompt-based metrics for measuring the difficulty level of educational texts, aiming to improve upon traditional static metrics like Flesch-Kincaid for assessing whether LLM-generated content is appropriately adapted to different education levels. The work focuses on developing better evaluation methods for measuring how well AI systems adapt educational content difficulty, combining LLM-based prompts with traditional readability metrics.

This paper introduces STANDARDIZE, a framework for aligning LLM-generated content with expert-defined educational standards (CEFR and Common Core Standards) through retrieval-style in-context learning, focusing on generating text content at appropriate reading levels for language learners.

This paper evaluates the ability of large language models (ChatGPT, Copilot, Claude) to personalize board games for educational use by suggesting modifications aligned with specific classroom contexts and learning objectives, comparing AI-generated suggestions against human expert recommendations.

This study compares lesson plans created by human curriculum designers versus two GenAI models (fine-tuned LLaMA-2-13b and customized GPT-4) in K-12 mathematics education, evaluating educator preferences across instructional components (warm-up, main task, cool-down) and grade levels. The mixed-methods analysis examines both quantitative preferences and qualitative feedback to identify strengths and limitations of AI-generated lesson plans compared to human-authored ones.

This study evaluates ChatGPT-generated resources for K-12 information literacy education using Common Sense Media's Digital Citizenship framework as a template, assessing the suitability and effectiveness of AI-generated instructional materials for teaching digital citizenship concepts.

This paper investigates how different prompt engineering strategies affect the cognitive alignment of AI-generated quiz questions with Bloom's Taxonomy levels in OneClickQuiz, a Moodle plugin for automated quiz generation. The study evaluates three prompt variants using automated classification and human review to determine which approaches best ensure pedagogically appropriate question generation at intended cognitive levels.

This paper evaluates instruction-tuned language models (ChatGPT, BLOOMZ, FlanT5, Llama) on their ability to generate and simplify text at specified readability levels using standard metrics like Flesch-Kincaid Grade Level and CEFR, tasks commonly performed by teachers when creating educational materials.

COGENT is a framework for generating curriculum-aligned, grade-appropriate science reading materials using LLMs, incorporating NGSS standards, readability controls, and wonder-based learning approaches. The paper evaluates generated content across curriculum alignment, comprehensibility, and readability metrics using both LLM-as-judge and human expert analysis.

This paper introduces a GenAI-powered digital assistant that uses an 'interactive mega-prompt' system to help educators create customized lesson plans tailored to student demographics, learning objectives, and teaching styles. The tool was evaluated for effectiveness through quantitative metrics (time savings) and qualitative feedback (user satisfaction) from educators across various subjects and educational levels.

This paper fine-tunes IndoBERT to automatically classify Indonesian elementary school exam questions according to Bloom's Taxonomy cognitive levels, achieving 97% accuracy. The system aims to reduce teachers' manual workload in categorizing questions by cognitive difficulty.

This paper develops and compares multiple machine learning approaches (traditional ML, RNNs, transformers, and LLMs) to automatically classify exam questions and learning outcomes according to Bloom's Taxonomy cognitive levels using a dataset of 600 labeled sentences. The study finds that augmented Support Vector Machines achieve the best performance (94% accuracy) while deep learning models suffer from overfitting on the small dataset.

This paper develops a method to control pre-trained language models for grade-specific text simplification, predicting low-level edit operations needed to simplify texts to specific reading grade levels (grades 3-8). The work focuses on automatic text rewriting to match target grade-level readability rather than evaluating learning outcomes or pedagogical effectiveness.

This paper evaluates GPT-4's ability to automatically grade short answer questions in K-12 education (ages 5-16) across Science and History using a novel dataset from the Carousel quizzing platform, finding performance (Kappa 0.70) close to human-level (0.75). The study demonstrates that LLMs can reliably perform formative assessment grading tasks across multiple subjects and grade levels with minimal prompt engineering.

EduEval is a comprehensive hierarchical benchmark for evaluating LLMs in Chinese K-12 education, comprising 24 task types with over 11,000 questions organized across six cognitive dimensions (Memorization, Understanding, Application, Reasoning, Creativity, and Ethics) based on Bloom's Taxonomy and Webb's Depth of Knowledge. The benchmark uses authentic educational materials including real exam questions, classroom dialogues, student essays, and expert-designed prompts spanning primary through high school levels.

This paper evaluates LLM-based and statistical NLP methods for automated scoring of nationwide high school graduation essay exams in Estonia, comparing machine-generated scores against human raters across multiple rubric dimensions including content, argumentation, and language quality. The study demonstrates that automated scoring achieves reliability comparable to human raters while also examining bias, prompt injection risks, and providing personalized feedback capabilities.

This paper develops a chain-of-thought prompting approach using GPT-4 to automatically score and generate explanations for middle school Earth Science formative assessment responses, employing human-in-the-loop few-shot and active learning methods. The system evaluates open-ended short-answer responses and provides meaningful feedback to support student learning.

This paper presents a co-design pilot study with 19 K-12 teachers examining the classroom implementation of an AI-powered grading platform (Colleague AI) that generates rubrics and provides automated feedback on student work. Through usage logs, surveys, and interviews, the study evaluates teacher and student perspectives on AI-generated scoring versus narrative feedback, revealing trust issues with automated grading but appreciation for rapid formative feedback.

This paper evaluates state-of-the-art VLMs and LLMs on grading over 14,000 handwritten answers from Indonesian Grade 4 students in Mathematics and English, and generating personalized feedback. The study introduces a multimodal pipeline integrating vision models for handwriting recognition and language models for rubric-based assessment in real-world, underrepresented classroom settings.

This paper compares three models (fine-tuned Mistral/GOAT, SBERT-Canberra, and GPT-4) for automatically scoring and providing qualitative feedback on middle-school students' open-ended math responses, evaluating both scoring accuracy and feedback quality using teacher judgments.

EduBench introduces a comprehensive benchmark dataset with 18,821 data points across 9 educational scenarios and 4,000+ educational contexts (covering K-12 and higher education subjects, different difficulty levels, and multiple question types), evaluated using 12 multi-dimensional metrics covering scenario adaptation, factual/reasoning accuracy, and pedagogical application. The benchmark assesses LLM capabilities in diverse educational tasks including assignment grading, study planning, tutoring, and psychological counseling, with both human and automated evaluation.

This paper introduces PBLBench, a benchmark for evaluating multimodal large language models (MLLMs) on their ability to assess STEM Project-Based Learning (PBL) outcomes, including evaluating research reports, code, experimental data, and videos using expert-validated criteria derived through the Analytic Hierarchy Process (AHP). The benchmark tests 15 MLLMs on grading and ranking PBL projects across multiple STEM disciplines with long-context multimodal inputs.

This paper investigates how assessment construct characteristics (complexity, diversity, structure) affect machine learning model performance when automatically scoring middle school students' written scientific argumentation responses across 17 assessment tasks aligned to K-12 science education standards (NGSS).

This paper develops and evaluates automated methods using large language models (GPT-4, GPT-4-mini, and ModernBERT) to assess critical thinking subskills in student-written argumentative essays, comparing zero-shot prompting, few-shot prompting, and supervised fine-tuning approaches against human coding. The work focuses on measuring higher-order reasoning skills including understanding/analyzing information, evaluating evidence, making inferences, and articulating arguments.

This paper presents a multi-agent LLM system for automatically generating multiple-choice questions (MCQs) to assess AI literacy in K-12 students (grades 7-9), using critique agents to ensure questions align with learning objectives, grade levels, and Bloom's Taxonomy. Three K-12 AI literacy teaching experts evaluated 40 generated questions using a pedagogical quality rubric.

This survey paper systematically reviews LLM applications in education from a technology-centric perspective, covering student/teacher assistance, adaptive learning, and commercial tools, while organizing related datasets, benchmarks, and identifying deployment challenges. It provides a comprehensive taxonomy of how LLMs are being applied across multiple educational contexts including tutoring, assessment, content generation, and personalized learning.

This survey paper comprehensively reviews LLM agents for education, proposing a task-centric taxonomy that categorizes agents based on teaching assistance (classroom simulation, feedback generation, curriculum design) and student support (adaptive learning, knowledge tracing, error correction). The paper analyzes architectures, datasets, benchmarks, and deployment challenges including ethics, hallucination, and overreliance.

This paper evaluates Large Language Models (ChatGPT and Llama) for automated essay scoring by comparing their grades to human raters using the ASAP dataset, finding that LLMs assign lower scores that correlate poorly with human evaluations, though they reliably detect spelling and grammar mistakes.

Grade Guard is an LLM-based framework for automated short answer grading that introduces an Indecisiveness Score to reflect grading uncertainty and enables human re-evaluation when confidence is low. The system uses fine-tuned temperature parameters and confidence-aware loss to improve grading accuracy compared to baseline LLM approaches.

This paper examines how large language models can be integrated into educational grading practices, analyzing their potential to automate assessment, provide personalized feedback, and improve consistency while addressing challenges like bias, data privacy, and ethical concerns in automated grading systems.

This paper is a systematic review of large language models (LLMs) used as virtual tutors in education, examining applications including automatic question generation, student assessment, feedback provision, and personalized learning across K-12 and higher education contexts. The review analyzes how LLMs like GPT-3 and BERT are deployed for educational tasks such as generating explanations, grading answers, and providing tutoring support.

This white paper examines ethical implications of AI-powered tools in educational measurement, focusing on automated scoring, personalized feedback, and data analytics while addressing concerns about validity, reliability, transparency, fairness, algorithmic bias, and equity in educational assessment contexts.

This paper proposes using DeBERTa with Adversarial Weights Perturbation and Metric-specific AttentionPooling to improve automated essay scoring specifically for English Language Learners (ELLs), focusing on optimizing hyperparameters to better evaluate writing proficiency.

EduEval is a comprehensive hierarchical benchmark for evaluating LLMs in Chinese K-12 education, comprising 24 task types with over 11,000 questions organized across six cognitive dimensions (Memorization, Understanding, Application, Reasoning, Creativity, and Ethics) based on Bloom's Taxonomy and Webb's Depth of Knowledge. The benchmark uses authentic educational materials including real exam questions, classroom dialogues, student essays, and expert-designed prompts spanning primary through high school levels.

FEANEL is a benchmark for evaluating LLMs' ability to provide fine-grained error analysis and pedagogical feedback on K-12 English writing, comprising 1,000 student essays with expert-annotated errors categorized by type, severity, and explanations. The benchmark specifically assesses whether AI systems can identify writing errors and provide educationally meaningful, interpretable feedback to support student learning.

This paper evaluates LLM-based and statistical NLP methods for automated scoring of nationwide high school graduation essay exams in Estonia, comparing machine-generated scores against human raters across multiple rubric dimensions including content, argumentation, and language quality. The study demonstrates that automated scoring achieves reliability comparable to human raters while also examining bias, prompt injection risks, and providing personalized feedback capabilities.

This paper develops and evaluates a pedagogical framework for LLM-driven feedback generation in secondary school Python programming education, aligning automated feedback with established pedagogical principles like mastery adaptation and progress-based scaffolding. Through mixed-method evaluation with eight secondary school computer science teachers, the study assesses how well LLM-generated feedback adheres to pedagogical standards compared to human teacher feedback.

This paper develops a chain-of-thought prompting approach using GPT-4 to automatically score and generate explanations for middle school Earth Science formative assessment responses, employing human-in-the-loop few-shot and active learning methods. The system evaluates open-ended short-answer responses and provides meaningful feedback to support student learning.

This paper evaluates the feasibility of using LLMs (GPT-4, Gemini, LearnLM) to automatically identify and assess two specific tutoring moves in real-life math tutoring dialogues: delivering effective praise and responding to student errors. The study analyzes 50 transcripts of college tutors working with middle school students, demonstrating that LLMs can reliably detect tutoring situations (94-98% accuracy for praise detection, 82-88% for error detection) and evaluate adherence to best practices (83-89% and 73-77% alignment with human judgment).

This paper develops an automated system using GPT-3.5 to evaluate five key tutoring strategies (praise, error reaction, knowledge assessment, managing inequity, responding to negative self-talk) in one-on-one tutoring dialogues, classifying whether each strategy is employed effectively or ineffectively. The system analyzes tutoring transcripts to provide color-coded feedback on pedagogical quality of tutor-student interactions.

This paper develops and evaluates a reinforcement learning framework for automatically generating pedagogically valid feedback for incorrect student answers in math education, using GPT-4 to evaluate feedback quality according to a rubric measuring both correctness and alignment with educational goals. The work demonstrates that fine-tuning Llama 2 with direct preference optimization significantly improves feedback quality across correctness and pedagogical alignment dimensions.

This paper evaluates CyberScholar, a GenAI writing assistant that provides formative feedback aligned with teacher rubrics to K-12 students (grades 7-11) across multiple subject areas. The study examines student and teacher perceptions through surveys and interviews in four U.S. schools, focusing on how AI feedback supports writing improvement, metacognition, and self-regulation.

This paper develops and evaluates a multi-agent AI system (AutoFeedback) to automatically generate feedback on student constructed responses in science assessments, specifically addressing issues of over-praise and over-inference found in single-agent LLM feedback. The system uses two agents—one to generate feedback and another to validate and refine it—and demonstrates significant improvements in feedback quality when tested on 240 student responses.

This paper presents a co-design pilot study with 19 K-12 teachers examining the classroom implementation of an AI-powered grading platform (Colleague AI) that generates rubrics and provides automated feedback on student work. Through usage logs, surveys, and interviews, the study evaluates teacher and student perspectives on AI-generated scoring versus narrative feedback, revealing trust issues with automated grading but appreciation for rapid formative feedback.

This is a three-day lesson plan for 9th-12th grade English Language Arts that uses AI writing assistants to help students analyze their writing through AI-enhanced rubrics, receive automated feedback, and engage in AI-informed peer review to revise their work. The lesson directly evaluates how AI tools impact student writing revision processes and self-assessment skills in an actual classroom setting.

This paper evaluates state-of-the-art VLMs and LLMs on grading over 14,000 handwritten answers from Indonesian Grade 4 students in Mathematics and English, and generating personalized feedback. The study introduces a multimodal pipeline integrating vision models for handwriting recognition and language models for rubric-based assessment in real-world, underrepresented classroom settings.

This paper develops and evaluates a generative AI-based system using ChatGPT to automatically assess and provide feedback on student argumentation writing by extracting argument components (claims, data, warrants, etc.). The system compares AI performance against human expert evaluation across scientific and non-scientific contexts for K-12 argumentation training.

This paper evaluates the quality and usefulness of educational questions generated by large language models (specifically GPT-3/InstructGPT) using controllable text generation with Bloom's taxonomy and difficulty levels, validated through teacher assessments across two domains. The study demonstrates that LLM-generated questions are judged by teachers as high quality and sufficiently useful for classroom use.

This paper evaluates the multilingual performance of large language models (GPT-4o, Gemini, Claude, Llama, Mistral) on four K-12 educational tasks: identifying student misconceptions, providing targeted feedback, interactive tutoring, and grading translations across nine languages including English, Mandarin, Hindi, Arabic, German, Farsi, Telugu, Ukrainian, and Czech.

This paper compares three models (fine-tuned Mistral/GOAT, SBERT-Canberra, and GPT-4) for automatically scoring and providing qualitative feedback on middle-school students' open-ended math responses, evaluating both scoring accuracy and feedback quality using teacher judgments.

EduBench introduces a comprehensive benchmark dataset with 18,821 data points across 9 educational scenarios and 4,000+ educational contexts (covering K-12 and higher education subjects, different difficulty levels, and multiple question types), evaluated using 12 multi-dimensional metrics covering scenario adaptation, factual/reasoning accuracy, and pedagogical application. The benchmark assesses LLM capabilities in diverse educational tasks including assignment grading, study planning, tutoring, and psychological counseling, with both human and automated evaluation.

This paper introduces PBLBench, a benchmark for evaluating multimodal large language models (MLLMs) on their ability to assess STEM Project-Based Learning (PBL) outcomes, including evaluating research reports, code, experimental data, and videos using expert-validated criteria derived through the Analytic Hierarchy Process (AHP). The benchmark tests 15 MLLMs on grading and ranking PBL projects across multiple STEM disciplines with long-context multimodal inputs.

This paper evaluates GPT-3.5-Turbo and GPT-4's ability to assess human tutors' performance in responding to K-12 students' math errors, specifically measuring whether tutors use indirect guidance strategies versus direct error correction. The study analyzes 50 real tutoring dialogues to determine if LLMs can provide automated feedback on tutoring quality.

EduEval is a comprehensive hierarchical benchmark for evaluating LLMs in Chinese K-12 education, comprising 24 task types with over 11,000 questions organized across six cognitive dimensions (Memorization, Understanding, Application, Reasoning, Creativity, and Ethics) based on Bloom's Taxonomy and Webb's Depth of Knowledge. The benchmark uses authentic educational materials including real exam questions, classroom dialogues, student essays, and expert-designed prompts spanning primary through high school levels.

This paper evaluates LLM-based and statistical NLP methods for automated scoring of nationwide high school graduation essay exams in Estonia, comparing machine-generated scores against human raters across multiple rubric dimensions including content, argumentation, and language quality. The study demonstrates that automated scoring achieves reliability comparable to human raters while also examining bias, prompt injection risks, and providing personalized feedback capabilities.

This paper directly evaluates AI integration in secondary education through teacher surveys and a sixth-grade classroom experiment, examining impacts on student engagement, critical thinking, retention, and over-reliance. The study specifically investigates cognitive offloading risks when students use AI tools like ChatGPT for homework, measuring whether AI promotes genuine learning or creates dependency.

MinorBench is a hand-built benchmark designed to evaluate how well LLMs refuse unsafe or age-inappropriate queries from children, based on a real-world case study of middle-school students using an LLM chatbot and a novel taxonomy of content-based risks specific to minors.

This survey paper systematically reviews LLM applications in education from a technology-centric perspective, covering student/teacher assistance, adaptive learning, and commercial tools, while organizing related datasets, benchmarks, and identifying deployment challenges. It provides a comprehensive taxonomy of how LLMs are being applied across multiple educational contexts including tutoring, assessment, content generation, and personalized learning.

This survey paper comprehensively reviews LLM agents for education, proposing a task-centric taxonomy that categorizes agents based on teaching assistance (classroom simulation, feedback generation, curriculum design) and student support (adaptive learning, knowledge tracing, error correction). The paper analyzes architectures, datasets, benchmarks, and deployment challenges including ethics, hallucination, and overreliance.

This paper examines how large language models can be integrated into educational grading practices, analyzing their potential to automate assessment, provide personalized feedback, and improve consistency while addressing challenges like bias, data privacy, and ethical concerns in automated grading systems.

This white paper examines ethical implications of AI-powered tools in educational measurement, focusing on automated scoring, personalized feedback, and data analytics while addressing concerns about validity, reliability, transparency, fairness, algorithmic bias, and equity in educational assessment contexts.

This paper develops methods to detect boundaries between human-written and AI-generated content in hybrid essays where students may have used LLMs like ChatGPT to complete portions of their writing assignments. The approach identifies transition points in student essays to help educators detect AI assistance in academic writing.

This paper comprehensively evaluates nine Automated Essay Scoring (AES) methods across 25,000+ student essays, examining the interplay between predictive accuracy, fairness (bias across demographic groups), and generalizability in both prompt-specific and cross-prompt settings. The study reveals that prompt-specific models achieve higher accuracy but exhibit greater bias toward students of different economic statuses compared to cross-prompt models.

This perspective article examines how AI integration affects classroom-based formative assessment practices, discussing both opportunities (e.g., automated feedback, data analytics) and challenges (e.g., potential for cognitive offloading, reduced critical thinking, over-reliance on AI-generated content) for teachers implementing formative assessment strategies.

This paper surveys students and teachers on their perceptions and experiences using ChatGPT in education, examining both opportunities (personalized feedback, accessibility, interactive learning, lesson preparation) and challenges (cheating risks, reduced critical thinking, academic integrity concerns). The study includes subjective experiments demonstrating ChatGPT's effectiveness in programming education and analyzes survey results to understand its impact on learning and teaching.

This qualitative study investigates programming instructors' perceptions of ChatGPT's potential benefits and drawbacks for computer programming education at a university, exploring how it can support personalized learning, code debugging, and instructional efficiency while raising concerns about over-reliance, accuracy, and ethical issues.

This Indonesian case study examines English language teachers' and learners' perceptions of using AI for literary writing instruction, finding that AI helps with lesson planning, content generation, and writing skill development, but also creates dependency that limits creativity and critical thinking. The research uses questionnaire data to assess both pedagogical benefits and concerns about cognitive offloading.

This paper investigates whether LLM judges can be manipulated through persuasive language when evaluating mathematical solutions, finding that strategically embedded rhetorical techniques cause LLMs to assign inflated scores to incorrect answers by up to 8%. The study tests 14 LLM models across six math benchmarks using seven persuasion strategies grounded in Aristotelian rhetoric.

This paper introduces CulturAIEd, an LLM-powered tool that helps K-12 teachers adapt AI literacy curricula to students' cultural contexts through Culturally Relevant Pedagogy (CRP) principles. A pilot study with four K-12 teachers explored how the tool influences their confidence and ability to design culturally responsive AI literacy activities.

This paper presents a framework for building child-centered machine learning pipelines and describes two case studies: one predicting classroom engagement levels using video and biosensor data to support teachers, and another developing a math learning game with handwriting recognition for K-12 students.

This paper benchmarks LLM-generated text detection methods in educational contexts using a novel dataset (GEDE) of student essays and LLM-generated texts across different 'contribution levels' (from fully human-written to fully AI-generated). The work evaluates state-of-the-art detectors' performance in identifying AI-generated student submissions, particularly examining false positive rates and detection across different levels of human-AI collaboration.

This paper investigates counterfactual fairness—a causal approach to algorithmic fairness—in machine learning models applied to educational datasets, examining whether decisions for students would remain the same if their demographic attributes (race, gender) were different. The work evaluates fairness and bias in predictive models used for academic success prediction, at-risk detection, and other educational decision-making contexts.

This paper evaluates eight publicly-available LLM-generated text detectors (including GPTZero, CopyLeaks, GPTKit, and GLTR) using computing education assignments from university students, comparing their accuracy, false positive rates, and resilience to paraphrasing tools. The study focuses on detecting academic integrity violations when students use ChatGPT to complete assignments, finding significant variation in detector performance and high false positive rates.