搜索结果：educational

Analogies help learners understand unfamiliar concepts by relating them to known concepts. Despite recent advances, large language models (LLMs) continue to struggle to generate analogies of comparable quality to those produced by humans. We present a modular pipeline for educational analogy generation, decomposing the task into four stages: source finding, sub-concept generation, explanation generation, and evaluation. Grounded in Structure Mapping Theory, the pipeline enables systematic, stage-by-stage analysis of how model choice and input configuration affect analogy quality. We evaluate 12 state-of-the-art LLMs across six model families on two datasets with structured sub-concept annotations (SCAR and ParallelPARC), alongside seven embedding models for closed-setting retrieval. Our results show that sub-concepts substantially improve explanation quality and closed setting retrieval precision but provide limited benefit in open-ended source generation. We further introduce an LLM-as-a-judge evaluation methodology and validate its scoring against human annotations from seven annotators, finding that Claude Sonnet 4.6 aligns more reliably with human rankings than with fine-graine

To advance Educational Data Mining (EDM) within strict privacy-protecting regulatory frameworks, researchers must develop methods that enable data-driven analysis while protecting sensitive student information. Synthetic data generation is one such approach, enabling the release of statistically generated samples instead of real student records; however, existing deep learning and parametric generators often distort marginal distributions and degrade under iterative regeneration, leading to distribution drift and progressive loss of distributional support that compromise reliability. In response, we introduce the Non-Parametric Gaussian Copula (NPGC), a plug-and-play synthesis method that replaces deep learning and parametric optimization with empirical statistical anchoring to preserve the observed marginal distributions while modeling dependencies through a copula framework. NPGC integrates Differential Privacy (DP) at both the marginal and correlation levels, supports heterogeneous variable types, and treats missing data as an explicit state to retain informative absence patterns. We evaluate NPGC against deep learning and parametric baselines on five benchmark datasets and demo

Knowing how test takers answer items in educational assessments is essential for test development, to evaluate item quality, and to improve test validity. However, this process usually requires extensive pilot studies with human participants. If large language models (LLMs) exhibit human-like response behavior to test items, this could open up the possibility of using them as pilot participants to accelerate test development. In this paper, we evaluate the human-likeness or psychometric plausibility of responses from 18 instruction-tuned LLMs with two publicly available datasets of multiple-choice test items across three subjects: reading, U.S. history, and economics. Our methodology builds on two theoretical frameworks from psychometrics which are commonly used in educational assessment, classical test theory and item response theory. The results show that while larger models are excessively confident, their response distributions can be more human-like when calibrated with temperature scaling. In addition, we find that LLMs tend to correlate better with humans in reading comprehension items compared to other subjects. However, the correlations are not very strong overall, indicat

In modular educational systems, students are allowed to choose a part of their own curriculum themselves. This is typically done in the final class levels which lead to maturity for university access. The rationale behind letting students choose their courses themselves is to enhance self-responsibility, improve student motivation, and allow a focus on specific areas of interest. A central instrument for bringing these systems to fruition is the timetable. However, scheduling the timetable in such systems can be an extremely challenging and time-consuming task. In this study, we present a framework for classifying modular educational systems in Europe that reflects different degrees of freedom regarding student choices, and explore the consequences from the perspective of scheduling a timetable that satisfies all requirements from the organizational and the pedagogical perspective. For this purpose, we conducted interviews in Austria, Germany, Finland, Switzerland, the Netherlands, and Luxembourg and apply the framework to these educational systems, finding that among them the Finnish system shows the highest degree of modularity. After analyzing the consequences of modularity from

The growing integration of Artificial Intelligence (AI) into education has intensified the need for transparency and interpretability. While hackathons have long served as agile environments for rapid AI prototyping, few have directly addressed eXplainable AI (XAI) in real-world educational contexts. This paper presents a comprehensive analysis of the XAI Challenge 2025, a hackathon-style competition jointly organized by Ho Chi Minh City University of Technology (HCMUT) and the International Workshop on Trustworthiness and Reliability in Neurosymbolic AI (TRNS-AI), held as part of the International Joint Conference on Neural Networks (IJCNN 2025). The challenge tasked participants with building Question-Answering (QA) systems capable of answering student queries about university policies while generating clear, logic-based natural language explanations. To promote transparency and trustworthiness, solutions were required to use lightweight Large Language Models (LLMs) or hybrid LLM-symbolic systems. A high-quality dataset was provided, constructed via logic-based templates with Z3 validation and refined through expert student review to ensure alignment with real-world academic scen

This study introduces the AI-Educational Development Loop (AI-EDL), a theory-driven framework that integrates classical learning theories with human-in-the-loop artificial intelligence (AI) to support reflective, iterative learning. Implemented in EduAlly, an AI-assisted platform for writing-intensive and feedback-sensitive tasks, the framework emphasizes transparency, self-regulated learning, and pedagogical oversight. A mixed-methods study was piloted at a comprehensive public university to evaluate alignment between AI-generated feedback, instructor evaluations, and student self-assessments; the impact of iterative revision on performance; and student perceptions of AI feedback. Quantitative results demonstrated statistically significant improvement between first and second attempts, with agreement between student self-evaluations and final instructor grades. Qualitative findings indicated students valued immediacy, specificity, and opportunities for growth that AI feedback provided. These findings validate the potential to enhance student learning outcomes through developmentally grounded, ethically aligned, and scalable AI feedback systems. The study concludes with implication

Protecting Personally Identifiable Information (PII), such as names, is a critical requirement in learning technologies to safeguard student and teacher privacy and maintain trust. Accurate PII detection is an essential step toward anonymizing sensitive information while preserving the utility of educational data. Motivated by recent advancements in artificial intelligence, our study investigates the GPT-4o-mini model as a cost-effective and efficient solution for PII detection tasks. We explore both prompting and fine-tuning approaches and compare GPT-4o-mini's performance against established frameworks, including Microsoft Presidio and Azure AI Language. Our evaluation on two public datasets, CRAPII and TSCC, demonstrates that the fine-tuned GPT-4o-mini model achieves superior performance, with a recall of 0.9589 on CRAPII. Additionally, fine-tuned GPT-4o-mini significantly improves precision scores (a threefold increase) while reducing computational costs to nearly one-tenth of those associated with Azure AI Language. Furthermore, our bias analysis reveals that the fine-tuned GPT-4o-mini model consistently delivers accurate results across diverse cultural backgrounds and genders

Massive Open Online Courses (MOOCs) have greatly contributed to making education more accessible. However, many MOOCs maintain a rigid, one-size-fits-all structure that fails to address the diverse needs and backgrounds of individual learners. Learning path personalization aims to address this limitation, by tailoring sequences of educational content to optimize individual student learning outcomes. Existing approaches, however, often require either massive student interaction data or extensive expert annotation, limiting their broad application. In this study, we introduce a novel data-efficient framework for learning path personalization that operates without expert annotation. Our method employs a flexible recommender system pre-trained with reinforcement learning on a dataset of raw course materials. Through experiments on semi-synthetic data, we show that this pre-training stage substantially improves data-efficiency in a range of adaptive learning scenarios featuring new educational materials. This opens up new perspectives for the design of foundation models for adaptive learning.

TiniScript is an intermediate programming language designed for educational robotics, aligned with STEM principles to foster integrative learning experiences. With its minimalist single-line syntax, such as F(2, 80) , TiniScript simplifies robotic programming, allowing users to bypass complex code uploading processes and enabling realtime direct instruction transmission. Thanks to its preloaded interpreter, TiniScript decouples programming from hardware, significantly reducing wait times. Instructions can be sent wirelessly from any Bluetooth enabled device, making TiniScript adaptable to various robots. This adaptability optimizes iterative and collaborative learning, allowing students to focus on the creative aspects of robotics. This paper explores TiniScripts design principles, syntax, and practical applications, highlighting its potential to make robotics programming more accessible and effective in developing critical thinking skills.

Question generation (QG) is a natural language processing task with an abundance of potential benefits and use cases in the educational domain. In order for this potential to be realized, QG systems must be designed and validated with pedagogical needs in mind. However, little research has assessed or designed QG approaches with the input from real teachers or students. This paper applies a large language model-based QG approach where questions are generated with learning goals derived from Bloom's taxonomy. The automatically generated questions are used in multiple experiments designed to assess how teachers use them in practice. The results demonstrate that teachers prefer to write quizzes with automatically generated questions, and that such quizzes have no loss in quality compared to handwritten versions. Further, several metrics indicate that automatically generated questions can even improve the quality of the quizzes created, showing the promise for large scale use of QG in the classroom setting.

Increasingly, researchers have suggested the benefits of temporal analysis to improve our understanding of the learning process. Sequential pattern mining (SPM), as a pattern recognition technique, has the potential to reveal the temporal aspects of learning and can be a valuable tool in educational data science. However, its potential is not well understood and exploited. This chapter addresses this gap by reviewing work that utilizes sequential pattern mining in educational contexts. We identify that SPM is suitable for mining learning behaviors, analyzing and enriching educational theories, evaluating the efficacy of instructional interventions, generating features for prediction models, and building educational recommender systems. SPM can contribute to these purposes by discovering similarities and differences in learners' activities and revealing the temporal change in learning behaviors. As a sequential analysis method, SPM can reveal unique insights about learning processes and be powerful for self-regulated learning research. It is more flexible in capturing the relative arrangement of learning events than the other sequential analysis methods. Future research may improve

The integration of artificial intelligence (AI) in educational measurement has revolutionized assessment methods, enabling automated scoring, rapid content analysis, and personalized feedback through machine learning and natural language processing. These advancements provide timely, consistent feedback and valuable insights into student performance, thereby enhancing the assessment experience. However, the deployment of AI in education also raises significant ethical concerns regarding validity, reliability, transparency, fairness, and equity. Issues such as algorithmic bias and the opacity of AI decision-making processes pose risks of perpetuating inequalities and affecting assessment outcomes. Responding to these concerns, various stakeholders, including educators, policymakers, and organizations, have developed guidelines to ensure ethical AI use in education. The National Council of Measurement in Education's Special Interest Group on AI in Measurement and Education (AIME) also focuses on establishing ethical standards and advancing research in this area. In this paper, a diverse group of AIME members examines the ethical implications of AI-powered tools in educational measure

There has been a growing interest in developing learner models to enhance learning and teaching experiences in educational environments. However, existing works have primarily focused on structured environments relying on meticulously crafted representations of tasks, thereby limiting the agent's ability to generalize skills across tasks. In this paper, we aim to enhance the generalization capabilities of agents in open-ended text-based learning environments by integrating Reinforcement Learning (RL) with Large Language Models (LLMs). We investigate three types of agents: (i) RL-based agents that utilize natural language for state and action representations to find the best interaction strategy, (ii) LLM-based agents that leverage the model's general knowledge and reasoning through prompting, and (iii) hybrid LLM-assisted RL agents that combine these two strategies to improve agents' performance and generalization. To support the development and evaluation of these agents, we introduce PharmaSimText, a novel benchmark derived from the PharmaSim virtual pharmacy environment designed for practicing diagnostic conversations. Our results show that RL-based agents excel in task completi

The automatic generation of hints by Large Language Models (LLMs) within Intelligent Tutoring Systems (ITSs) has shown potential to enhance student learning. However, generating pedagogically sound hints that address student misconceptions and adhere to specific educational objectives remains challenging. This work explores using LLMs (GPT-4o and Llama-3-8B-instruct) as teachers to generate effective hints for students simulated through LLMs (GPT-3.5-turbo, Llama-3-8B-Instruct, or Mistral-7B-instruct-v0.3) tackling math exercises designed for human high-school students, and designed using cognitive science principles. We present here the study of several dimensions: 1) identifying error patterns made by simulated students on secondary-level math exercises; 2) developing various prompts for GPT-4o as a teacher and evaluating their effectiveness in generating hints that enable simulated students to self-correct; and 3) testing the best-performing prompts, based on their ability to produce relevant hints and facilitate error correction, with Llama-3-8B-Instruct as the teacher, allowing for a performance comparison with GPT-4o. The results show that model errors increase with higher te

Ensuring fairness is essential for every education system. Machine learning is increasingly supporting the education system and educational data science (EDS) domain, from decision support to educational activities and learning analytics. However, the machine learning-based decisions can be biased because the algorithms may generate the results based on students' protected attributes such as race or gender. Clustering is an important machine learning technique to explore student data in order to support the decision-maker, as well as support educational activities, such as group assignments. Therefore, ensuring high-quality clustering models along with satisfying fairness constraints are important requirements. This chapter comprehensively surveys clustering models and their fairness in EDS. We especially focus on investigating the fair clustering models applied in educational activities. These models are believed to be practical tools for analyzing students' data and ensuring fairness in EDS.

Jill Watson, a virtual teaching assistant powered by LLMs, answers student questions and engages them in extended conversations on courseware provided by the instructors. In this paper, we analyze student interactions with Jill across multiple courses and colleges, focusing on the types and complexity of student questions based on Bloom's Revised Taxonomy and tool usage patterns. We find that, by supporting a wide range of cognitive demands, Jill encourages students to engage in sophisticated, higher-order cognitive questions. However, the frequency of usage varies significantly across deployments, and the types of questions asked depend on course-specific contexts. These findings pave the way for future work on AI-driven educational tools tailored to individual learning styles and course structure, potentially enhancing both the teaching and learning experience in classrooms.

This paper describes the results of the first shared task on the generation of teacher responses in educational dialogues. The goal of the task was to benchmark the ability of generative language models to act as AI teachers, replying to a student in a teacher-student dialogue. Eight teams participated in the competition hosted on CodaLab. They experimented with a wide variety of state-of-the-art models, including Alpaca, Bloom, DialoGPT, DistilGPT-2, Flan-T5, GPT-2, GPT-3, GPT- 4, LLaMA, OPT-2.7B, and T5-base. Their submissions were automatically scored using BERTScore and DialogRPT metrics, and the top three among them were further manually evaluated in terms of pedagogical ability based on Tack and Piech (2022). The NAISTeacher system, which ranked first in both automated and human evaluation, generated responses with GPT-3.5 using an ensemble of prompts and a DialogRPT-based ranking of responses for given dialogue contexts. Despite the promising achievements of the participating teams, the results also highlight the need for evaluation metrics better suited to educational contexts.

Mapuzugun is the language of the Mapuche people. Due to political and historical reasons, its number of speakers has decreased and the language has been excluded from the educational system in Chile and Argentina. For this reason, it is very important to support the revitalization of the Mapuzugun in all spaces and media of society. In this work we present a tool towards supporting educational activities of Mapuzugun, tailored to the characteristics of the language. The tool consists of three parts: design and development of an orthography detector and converter; a morphological analyzer; and an informal translator. We also present a case study with Mapuzugun students showing promising results. Short Abstract in Mapuzuzgun: Tüfachi küzaw pegelfi kiñe zugun küzawpeyüm kelluaetew pu mapuzugun chillkatufe kimal kizu tañi zugun.

How can we test whether state-of-the-art generative models, such as Blender and GPT-3, are good AI teachers, capable of replying to a student in an educational dialogue? Designing an AI teacher test is challenging: although evaluation methods are much-needed, there is no off-the-shelf solution to measuring pedagogical ability. This paper reports on a first attempt at an AI teacher test. We built a solution around the insight that you can run conversational agents in parallel to human teachers in real-world dialogues, simulate how different agents would respond to a student, and compare these counterpart responses in terms of three abilities: speak like a teacher, understand a student, help a student. Our method builds on the reliability of comparative judgments in education and uses a probabilistic model and Bayesian sampling to infer estimates of pedagogical ability. We find that, even though conversational agents (Blender in particular) perform well on conversational uptake, they are quantifiably worse than real teachers on several pedagogical dimensions, especially with regard to helpfulness (Blender: Δ ability = -0.75; GPT-3: Δ ability = -0.93).