AIBearisharXiv – CS AI · 4d ago7/10
🧠Researchers introduced LiveK12Bench, a dynamic benchmark for evaluating Large Multimodal Models on realistic high school examinations across multiple disciplines. The study reveals that advanced LMMs like GPT-4 experience significant performance degradation when subjected to exam-realistic constraints, dropping from 79 to 53 points when process rigor and efficiency are jointly evaluated, exposing critical gaps between theoretical capabilities and practical educational readiness.
🧠 GPT-5
AIBearisharXiv – CS AI · May 117/10
🧠Research reveals that AI models, particularly few-shot large language models, struggle significantly with mid-range quality responses in automated short answer scoring, while fine-tuned models and human experts maintain consistent performance across all quality levels. This degradation raises fairness concerns for students with developing understanding, emphasizing the need for quality-conditioned evaluation metrics.
🧠 GPT-4🧠 GPT-5🧠 Claude
AIBearisharXiv – CS AI · Apr 147/10
🧠Researchers present Edu-MMBias, a comprehensive framework for detecting social biases in Vision-Language Models used in educational settings. The study reveals that VLMs exhibit compensatory class bias while harboring persistent health and racial stereotypes, and critically, that visual inputs bypass text-based safety mechanisms to trigger hidden biases.
AIBearisharXiv – CS AI · Mar 56/10
🧠A research study tested 11 AI tools on their ability to classify the cognitive demand of mathematical tasks, finding they achieved only 63% accuracy on average with no tool exceeding 83%. The tools showed systematic bias toward middle-category classifications and struggled with reasoning about underlying cognitive processes versus surface textual features.
🏢 Perplexity🧠 ChatGPT🧠 Claude
AINeutralarXiv – CS AI · Mar 47/102
🧠Research comparing Knowledge Tracing (KT) models to Large Language Models (LLMs) for predicting student responses found that specialized KT models significantly outperform LLMs in accuracy, speed, and cost-effectiveness. The study demonstrates that domain-specific models are superior to general-purpose LLMs for educational prediction tasks, with LLMs being orders of magnitude slower and more expensive to deploy.
AINeutralarXiv – CS AI · 2d ago6/10
🧠Researchers introduce AgentSchool, an LLM-powered multi-agent simulator that models student learning through state transitions rather than simple role-play, featuring cognitively growable student agents with knowledge graphs and adaptive teachers operating within the Zone of Proximal Development. The system addresses the challenge of validating educational AI interventions in real classrooms by creating a configurable simulation environment that reproduces plausible learning outcomes and social dynamics without requiring institutional constraints or ethical compromises of live trials.
AINeutralarXiv – CS AI · 2d ago6/10
🧠Researchers propose a modular architecture for educational AI chatbots designed to enforce pedagogical principles and prevent negative learning outcomes. The approach addresses structural limitations in current monolithic LLM solutions by incorporating targeted modules at different exercise-solving stages, enabling more transparent and controlled student guidance.
AINeutralarXiv – CS AI · 3d ago6/10
🧠Researchers developed an LLM-based pipeline that automatically tags learning resources with competencies from structured frameworks, combining language models with graph constraints and evidence extraction. The system achieved strong performance metrics (0.57 micro-F1, 0.82 MRR) while providing transparent, auditable evidence spans—outperforming traditional baselines and addressing the labor-intensive challenge of manual resource tagging in educational systems.
AINeutralarXiv – CS AI · 3d ago6/10
🧠Researchers compared two conditioning approaches in educational recommendation systems: context-based (using current student questions) versus memory-based (using persistent learner history). Memory-based conditioning produced more personalized, history-dependent behavior while context-based approaches showed stronger immediate responsiveness, suggesting that embedding-based similarity metrics alone are insufficient for capturing true personalization effects.
AINeutralarXiv – CS AI · 3d ago6/10
🧠Researchers propose REC-CBM, a novel machine learning model that combines concept bottleneck models with rubric-aware error correction to automate open-ended educational grading while maintaining transparency and interpretability. Unlike black-box LLM systems, REC-CBM allows educators to verify scoring decisions through human-interpretable concept reasoning, addressing the growing need for trustworthy automated grading in educational settings.
AINeutralarXiv – CS AI · 3d ago6/10
🧠KT4EQG is a new educational framework that combines knowledge tracing with AI-powered question generation to create personalized exercise questions for students. The system uses machine learning to model each student's knowledge state and generates customized questions designed to maximize learning outcomes, demonstrating superior effectiveness compared to non-personalized approaches.
AINeutralarXiv – CS AI · May 125/10
🧠Researchers propose MBP-KT, a machine learning framework that improves knowledge tracing by extracting collaborative learning patterns from student interaction sequences. The method transforms raw data into meta-behavioral patterns and injects this global collaborative information into various knowledge tracing models, demonstrating consistent performance improvements across real-world datasets.
AINeutralarXiv – CS AI · May 126/10
🧠Researchers introduce Probabilistic Logical Knowledge Tracing (PLKT), an interpretable AI framework that uses Beta-distributed probabilistic embeddings to model student knowledge states and predict learning performance. Unlike conventional deep learning approaches that rely on opaque deterministic embeddings, PLKT constructs transparent reasoning paths showing how past interactions influence predictions while maintaining superior accuracy compared to existing methods.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers evaluated prompt-injection defenses for educational LLM tutors, revealing inherent trade-offs between security, usability, and speed. A multi-layer safeguard pipeline achieved 46.34% attack bypass with zero false positives and 2.50ms latency, while competing systems like NeMo Guardrails eliminated bypasses but suffered 16.22% false positive rates and 1.3-second delays.
AINeutralarXiv – CS AI · May 115/10
🧠Researchers propose Cognitive Agent Compilation (CAC), a framework that uses large language models to create explicit, inspectable problem-solving agents for educational applications. The approach separates knowledge representation, problem-solving policy, and verification rules to make AI systems more controllable and transparent than standard LLMs, though it reveals trade-offs between interpretability and scalability.
AINeutralarXiv – CS AI · May 76/10
🧠Researchers evaluated three major LLMs (Claude, Gemini, ChatGPT) on multimodal physics problems and found a significant performance drop compared to text-only tasks, identifying visual processing as the primary failure mode. A structured dialogue intervention corrected 82% of errors overall and achieved 100% correction on visual processing errors, offering immediate solutions for educators without requiring model retraining.
🧠 ChatGPT🧠 Claude🧠 Gemini
AINeutralarXiv – CS AI · May 16/10
🧠Researchers introduce MEDS (Math Education Digital Shadows), a dataset of 28,000 personas from 14 LLMs designed to evaluate how language models reason about mathematics and report their confidence levels. The dataset integrates math proficiency with psychological measures like anxiety and self-efficacy, revealing that LLMs exhibit human-like biases including negative attitudes and overconfidence in mathematical reasoning.
🧠 Grok
AINeutralarXiv – CS AI · May 16/10
🧠Researchers introduce ESTBook, a pedagogical diagnostic benchmark containing 10,576 multimodal questions across five major English standardized tests, designed to evaluate whether large language models can exhibit faithful reasoning and identify student misconceptions rather than just achieving binary accuracy scores. The framework moves beyond traditional test-taking benchmarks by enriching questions with cognitive reasoning trajectories and distractor rationales, enabling better assessment of LLM capabilities as educational tutoring tools.
AINeutralarXiv – CS AI · Apr 156/10
🧠Researchers evaluated GPT-4o's ability to score physics exam responses using rubric-assisted scoring, finding that AI reliability matches human inter-rater consistency when rubrics are well-structured and granular. The study reveals that clear rubric design matters far more than LLM configuration choices, with performance declining on ambiguous mid-range responses.
🧠 GPT-4
AINeutralarXiv – CS AI · Apr 136/10
🧠Researchers developed PharmaSim Switch, an AI-powered educational platform that uses large language models to scaffold diagnostic reasoning in pharmacy technician training through two distinct pedagogical approaches: structuring and problematizing. A 63-student experiment found both methods effective, with structuring promoting more accurate participation and problematizing encouraging deeper constructive engagement, suggesting hybrid scaffolding strategies optimize learning outcomes.
AINeutralarXiv – CS AI · Apr 106/10
🧠Researchers introduce chain-of-illocution (CoI) prompting to improve source faithfulness in retrieval-augmented language models, achieving up to 63% gains in source adherence for programming education tasks. The study reveals that standard RAG systems exhibit low fidelity to source materials, with non-RAG models performing worse, while a user study confirms improved faithfulness does not compromise user satisfaction.
AINeutralarXiv – CS AI · Apr 76/10
🧠Researchers developed a four-layer pedagogical safety framework for AI tutoring systems and introduced the Reward Hacking Severity Index (RHSI) to measure misalignment between proxy rewards and genuine learning. Their study of 18,000 simulated interactions found that engagement-optimized AI agents systematically selected high-engagement actions with no learning benefits, requiring constrained architectures to reduce reward hacking.
AINeutralarXiv – CS AI · Mar 96/10
🧠Researchers introduced VisioMath, a new benchmark with 1,800 K-12 math problems designed to test Large Multimodal Models' ability to distinguish between visually similar diagrams. The study reveals that current state-of-the-art models struggle with fine-grained visual reasoning, often relying on shallow positional heuristics rather than proper image-text alignment.
AIBearisharXiv – CS AI · Mar 36/106
🧠Research reveals that leading foundation models (LLMs) perform poorly on real-world educational tasks despite excelling on AI benchmarks. The study found that 50% of misalignment errors are shared across models due to common pretraining approaches, with model ensembles actually worsening performance on learning outcomes.
AINeutralarXiv – CS AI · Mar 26/1019
🧠Researchers developed BRIDGE, a framework to reduce bias in AI-powered automated scoring systems that unfairly penalize English Language Learners (ELLs). The system addresses representation bias by generating synthetic high-scoring ELL samples, achieving fairness improvements comparable to using additional human data while maintaining overall performance.
