The team, led by Haiping Ma and Xingyi Zhang, frames the problem as zero-shot cross-domain cognitive diagnosis, abbreviated ZCCD. Cognitive diagnosis is the task of estimating a student’s mastery of fine-grained knowledge concepts, such as specific skills within mathematics or language learning, from their response logs. Classical diagnostic models, including neural approaches developed over the past several years, excel when they can train on abundant interaction records within a single domain. But when a platform expands into a new subject, there are no logs to learn from. The researchers call this the diagnostic system cold-start problem, and it has become one of the central bottlenecks in intelligent education as online learning expands rapidly across subjects and institutions.

Previous attempts at cold-start diagnosis have tried to engineer around the missing data. Some approaches transfer embeddings of knowledge concepts across domains using concept graphs, while others rely on a small batch of early students in the target domain to bootstrap the model. These methods help, but they still require some structural alignment between domains or some minimal target-domain data. The Anhui team asked a more radical question: could a general-purpose large language model, with no fine-tuning and no target-domain response logs at all, act as the bridge between domains? Their answer is a paradigm they call large language model-guided cognitive state transfer, or LCST.

The core insight of LCST is to recast cognitive diagnosis as a natural language task. Instead of representing a student’s knowledge state as a vector of latent parameters learned by a neural network, the method expresses it in words. The system prompts a large language model with descriptions of the knowledge concepts in the source domain, the student’s recorded performance on exercises covering those concepts, and descriptions of the concepts in the target domain. The model is then asked to reason about which target-domain abilities the student is likely to have mastered, given the profile of strengths and weaknesses observed in the source domain. In effect, the language model serves as an intermediary that interprets a learner’s cognitive state in one subject and projects it into another.

What makes this plausible is the way large language models encode relationships between concepts. Because these models are trained on vast corpora of educational and general text, they carry implicit knowledge about how skills relate to one another, for example that proficiency in algebraic manipulation tends to accompany proficiency in solving linear equations, or that grammatical understanding underpins reading comprehension. The researchers exploit this by having the model analyze the relationships between knowledge concepts in both domains and use those relationships to guide the transfer of mastery estimates. The approach draws on techniques such as chain-of-thought prompting, which encourages models to reason step by step rather than jumping to conclusions, and prompt engineering, which shapes the input format so the model can best apply its internal knowledge to the diagnostic task.

The team evaluated LCST on real-world datasets, including educational data spanning multiple subject domains, and compared it against existing cold-start and transfer-learning baselines for cognitive diagnosis. The results showed that the language-model-guided approach significantly improved diagnostic performance in the target domain compared with methods that lacked access to such semantic reasoning. Notably, the model achieved this without any prior interaction data from the target domain, which is precisely the condition under which conventional diagnostic models fail completely. The experiments used several prominent language models, including open-weight families such as Llama and Gemma as well as more capable proprietary systems, suggesting that the paradigm is not tied to a single proprietary model but reflects a general capability of modern language models.

The technical evaluation relied on standard metrics from the diagnostic modeling literature, including measures of how well predicted mastery patterns align with actual student performance, evaluated with area-under-the-curve style criteria commonly used to assess binary classification quality. The authors also situate their work within a rapidly growing body of research showing that large language models can act as zero-shot reasoners across many tasks, from ranking items in recommender systems to tracking dialogue states, without task-specific training. The cognitive diagnosis result extends this pattern to a domain where the underlying data, student response logs, are sparse, noisy, and structurally different from the text corpora the models were trained on.

The implications for education technology could be substantial. A platform that adds a new course area today typically needs weeks or months of usage before its recommendation and assessment engines become useful. If a language model can bootstrap reasonable diagnostic estimates immediately, platforms could deliver personalized exercise recommendations and ability assessments from day one, improving early learner engagement and reducing dropout during the vulnerable initial period. The approach also hints at a broader role for language models in education: rather than serving only as content generators or chat tutors, they may function as inferential engines that reason about learner cognition, a role the authors describe as language models acting as educational experts.

There are, of course, important caveats. The method depends on the quality and cultural coverage of the language model’s internal knowledge, and prior work has documented biases in how these models treat different topics and regions. Diagnostic estimates produced without any target-domain data will inevitably be less precise than those refined by actual interaction logs, so the most realistic deployment may treat zero-shot transfer as a starting point that is progressively corrected as real data accumulates. Interpretability is another consideration: because the model reasons in natural language, its justifications can in principle be inspected by educators, but those explanations must be validated rather than taken at face value. The Anhui team’s work, published in Frontiers of Digital Education and supported by the National Natural Science Foundation of China, nonetheless marks a striking demonstration that the semantic knowledge inside large language models can substitute, at least partially, for the statistical history that diagnostic systems have always required. As intelligent education systems spread to new subjects, languages, and regions, the ability to diagnose learners without waiting for data may prove to be one of the most consequential applications of language models in the classroom.

Subject of Research: Zero-shot cross-domain cognitive diagnosis of student knowledge using large language models

Article Title: Large Language Models Are Zero-Shot Cross-Domain Diagnosticians in Cognitive Diagnosis

Article References: Large Language Models Are Zero-Shot Cross-Domain Diagnosticians in Cognitive Diagnosis. (n.d.). https://doi.org/10.1007/s44366-025-0054-y

Image Credits: AI Generated

DOI: 10.1007/s44366-025-0054-y

Keywords: cognitive diagnosis, large language models, zero-shot learning, cold-start problem, intelligent education, prompt engineering, knowledge tracing, educational data mining, cross-domain transfer, AI in education, personalized learning, intelligent tutoring systems

The technical foundation of this shift lies in the architecture of large language models. These systems are trained on vast text corpora and learn statistical patterns of language that allow them to generate coherent explanations, solve problems, draft essays, and answer questions across virtually every academic discipline. Unlike earlier educational software, which followed rigid, pre-programmed rules, generative models produce novel responses tailored to each prompt. Wu and Chen point to DeepSeek, an open-source large language model developed for Chinese education research, as an example of how accessible, high-capability AI can empower learners across an entire society rather than remaining locked behind expensive proprietary systems. Open-source approaches matter because they allow universities to inspect, adapt, and integrate models into their own platforms without depending entirely on a handful of commercial vendors, a consideration that touches on cost, sovereignty, and pedagogical control.

One of the most concrete applications the editorial highlights is cognitive diagnosis, the task of figuring out precisely what a student knows and where their understanding breaks down. A companion study by Dong, Chen, and Wu introduces a model-agnostic framework that uses large language models together with the Solo taxonomy, a classification scheme for levels of understanding, to diagnose learners’ cognitive states. Related work by Ma and colleagues demonstrates that large language models can act as zero-shot cross-domain diagnosticians, meaning they can assess knowledge in subject areas they were never explicitly trained to evaluate. The technical significance is considerable: traditional diagnostic systems required large amounts of labeled response data for each specific domain, whereas language-model-based approaches can generalize across subjects. For universities, this means assessment could evolve from infrequent, high-stakes examinations toward continuous, fine-grained feedback that identifies misconceptions the moment they appear.

Mathematical reasoning remains a demanding benchmark for these systems, and the editorial’s reference list acknowledges the challenge directly. Liu and colleagues present MathEval, a comprehensive benchmark designed to evaluate how well large language models handle mathematical reasoning across difficulty levels and topic areas. Mathematics exposes both the power and the fragility of generative models: they can often produce elegant solution steps, yet they may also fail in ways that look convincing to a novice. This is precisely why the human-in-the-loop framing matters. In a collaborative paradigm, the AI proposes, explains, and drills; the instructor verifies, contextualizes, and corrects. The division of labor plays to the strengths of each side, with machines providing tireless availability and breadth while humans supply judgment, accountability, and the ability to recognize when an answer is plausible but wrong.

Personalization is the second pillar of the paradigm shift. Li, Chai, and colleagues explore how detailed student portraits, structured profiles built from learning behavior, performance data, and preferences, can drive personalized learning at scale. Tu, Chen, and Huang examine the mechanisms by which generative AI empowers personalized learning, along with the challenges and pathways institutions must navigate. Combined with diagnostic models, such portraits allow an AI tutor to adapt explanations to an individual student’s level, pace, and prior knowledge in ways a single lecturer facing hundreds of students never could. The editorial situates these capabilities within the characteristics of Generation Z, a cohort that has grown up with interactive digital environments and often expects immediate, individualized feedback. For these students, a static textbook and a weekly lecture are no longer the default interface to knowledge; conversational, adaptive systems are.

The editorial also engages with the geopolitical and cultural dimensions of educational AI. A commentary by Wang argues that DeepSeek’s Chinese-style innovation reinforces China’s educational confidence, while Wu’s own companion piece describes DeepSeek as a vehicle for global education empowerment for a whole society. The underlying point transcends any single model: when capable AI systems are open and affordable, they can reach institutions and learners who have historically been excluded from elite educational resources. The authors suggest that the paradigm shift is therefore not only pedagogical but also structural, potentially redistributing access to high-quality tutoring, feedback, and content creation. At the same time, the emphasis on open models reflects a recognition that educational AI embedded in one nation’s values and curricula will not automatically transfer to another, making locally adaptable systems essential.

None of this enthusiasm is presented without caution. The editorial and the studies it accompanies repeatedly stress that generative models hallucinate, produce confident errors, and can be misused for academic dishonesty. Krause, Panchal, and Ubhe assess the transformative impact of generative AI on higher education and document how institutions are wrestling with questions of assessment design, skill development, and the changing role of the lecturer. If an AI can draft an essay in seconds, universities must rethink what written assignments are meant to measure and how to evaluate the process of thinking rather than only the final product. The collaborative paradigm implies that assessment itself must evolve, rewarding students for how effectively they direct, question, and verify AI output, a skill the authors implicitly treat as a new form of literacy.

Zhu, Wang, and colleagues extend the discussion to K-12 education, surveying current trends and future prospects for large-scale foundation models in schools. Their inclusion in the editorial’s reference frame signals that the paradigm shift begins long before university. Students arriving on campus will already be accustomed to AI-assisted learning, and higher education institutions that fail to adapt risk offering an experience that feels outdated to their own applicants. The technical trajectory supports this expectation: foundation models are becoming multimodal, capable of processing text, images, and diagrams, and increasingly efficient enough to run in settings with limited computing infrastructure. Wu and Chen’s argument is that universities should lead this integration deliberately, shaping tools to pedagogical goals, rather than reacting after the fact to technologies students have already adopted on their own.

What emerges from the editorial is a vision of higher education in which the lecturer’s role is elevated rather than diminished. Freed from repetitive explanation and routine grading support, instructors can focus on mentorship, critical thinking, ethical reasoning, and the design of learning experiences that machines cannot supply. The AI handles scale; the human handles meaning. Wu and Chen describe this as a paradigm shift in the strict sense, a change in the underlying assumptions of the field rather than an incremental tool upgrade. Their position as editors of the journal, disclosed and excluded from the peer-review of their own piece, underscores how seriously the academic publishing community is taking the question. As generative models continue to improve, the institutions that thrive will likely be those that treat the human-AI partnership not as a compromise to be managed but as the defining educational relationship of the coming decades.

Subject of Research: Human-AI collaboration and large language models in higher education

Article Title: Collaboration of Generative AI and Human: Paradigm Shift for Higher Education

Article References: Wu, F., & Chen, J. (2025). Collaboration of Generative AI and Human: Paradigm Shift for Higher Education. Frontiers of Digital Education, 2(2), Article 24. https://doi.org/10.1007/s44366-025-0061-z

Image Credits: AI Generated

DOI: 10.1007/s44366-025-0061-z

Keywords: generative AI, large language models, higher education, DeepSeek, personalized learning, cognitive diagnosis, educational technology, paradigm shift, open-source AI, assessment, Generation Z, Zhejiang University

The problem the researchers set out to solve is one that statisticians call the cold-start scenario, and it is endemic to intelligent tutoring systems. Conventional cognitive diagnosis models, ranging from classical item response theory approaches developed in the 1950s to modern neural architectures, learn by observing patterns in student response data. They estimate latent traits, such as mastery of specific knowledge concepts, by correlating responses across many learners and many items. But when a learner has answered only a handful of questions, or when an exercise is brand new to the question bank, the statistical signal becomes vanishingly thin. The diagnosis then defaults to guesswork, and any recommendation built on that diagnosis inherits the error. In real educational platforms, where millions of learners arrive with sparse histories, this is not a marginal inconvenience but a central bottleneck.

Large language models would seem to offer an obvious remedy. These models, trained on enormous corpora of text, encode rich knowledge about academic subjects, about how concepts relate to one another, and about what makes a question difficult. In principle, an LLM could look at a student’s answer history and a question’s text and reason about the student’s understanding in a way that no purely statistical model could. But the researchers identified two fundamental obstacles to simply plugging an LLM into an existing diagnosis pipeline. First, while LLMs excel at semantic comprehension, they are surprisingly poor at capturing the fine-grained, interactive behavioral patterns that cognitive diagnosis depends on, such as the subtle correlations between a learner’s response trajectory and their underlying skill profile. Second, and more technically thorny, the internal representation spaces of the two systems are fundamentally incompatible: an LLM’s embeddings live in a semantic space shaped by language, while a cognitive diagnosis model’s features live in a behavioral space shaped by response data. Bridging these two worlds is not straightforward.

The solution proposed by the Zhejiang University team is a framework that is deliberately model-agnostic, meaning it can be attached to virtually any existing cognitive diagnosis architecture without redesigning that architecture from scratch. The framework draws on a venerable piece of educational theory: the SOLO taxonomy, short for Structure of the Observed Learning Outcome, developed by John Biggs and Kevin Collis in 1982. This taxonomy classifies the quality of a learner’s understanding into hierarchical levels, from shallow, unistructural responses that grasp isolated elements, through multistructural and relational levels where concepts are connected, up to extended abstract levels where understanding generalizes to new domains. By anchoring the LLM’s judgments in this well-established pedagogical structure, the framework ensures that the language model’s assessments are not free-form guesses but disciplined evaluations aligned with how learning researchers actually measure understanding.

The framework operates in two distinct stages. The first stage, which the authors call LLM diagnosis, uses the language model to assess learners through educational techniques, producing a richer and more comprehensive knowledge representation than response data alone could provide. Rather than relying solely on the binary record of right and wrong answers, the LLM evaluates the substance of learning outcomes, effectively acting as an expert teaching assistant who has read the textbook, seen the exercises, and can reason about what a particular pattern of answers implies about conceptual mastery. This stage injects domain knowledge into the system precisely where conventional models are weakest: for the rare learners and infrequently attempted items where behavioral data runs dry.

The second stage, cognitive level alignment, is where the technical ingenuity of the work becomes most apparent. The semantic representations produced by the LLM and the behavioral feature vectors computed by the cognitive diagnosis model inhabit different mathematical spaces, and naively concatenating them would produce noise rather than insight. To reconcile the two, the researchers employ contrastive learning, a technique that trains the model to pull together representations that describe the same underlying cognitive state while pushing apart representations that describe different states. This approach builds on supervised contrastive learning methods that have proven powerful in computer vision and representation learning more broadly. Alongside contrastive learning, the framework uses mask-reconstruction learning, inspired by masked autoencoders, in which portions of the representation are deliberately hidden and the model must reconstruct them from the remaining context. This forces the aligned representations to retain genuinely informative structure rather than memorizing superficial correspondences.

The elegance of this two-stage design lies in its division of labor. The LLM contributes what it is good at, namely deep semantic understanding of educational content and learning outcomes structured by the SOLO taxonomy, while the cognitive diagnosis model retains what it is good at, namely modeling the interactive behavioral dynamics of learners responding to exercises over time. The alignment stage then acts as a translator, ensuring that the semantic knowledge flows into the behavioral model without distortion. Because the framework is model-agnostic, it can enhance a range of existing diagnosis architectures, from classical probabilistic models like DINA to modern neural approaches, without requiring their internal mechanics to be rewritten. This plug-and-play quality matters enormously for practical adoption, since educational platforms have invested heavily in existing diagnosis pipelines and cannot afford to rebuild them from the ground up.

The empirical evaluation, conducted on multiple real-world datasets, demonstrated that the proposed framework significantly improves diagnostic accuracy compared with conventional approaches. The gains were particularly meaningful in exactly the scenarios that motivated the work: situations involving learners and items with limited observational data, where traditional models struggle most. The authors’ earlier related work, presented as a preprint titled Knowledge is Power: Harnessing Large Language Models for Enhanced Cognitive Diagnosis, laid the groundwork for this line of research, and the published framework refines it with the SOLO taxonomy structure and the dual alignment objectives. The datasets used in the evaluation include cross-course collections designed to test performance in cold-start conditions, ensuring that the reported improvements reflect the challenging deployment scenarios that matter in practice rather than only favorable data-rich regimes.

The broader implications of this research extend well beyond a single benchmark improvement. Intelligent education systems are proliferating worldwide, and the quality of every adaptive recommendation, every personalized learning path, and every automated feedback message ultimately rests on the accuracy of the underlying cognitive diagnosis. If large language models can serve as knowledge engines that make diagnosis robust even for the newest student or the freshest question, the ceiling on what personalized learning platforms can achieve rises considerably. The work also exemplifies a growing pattern in artificial intelligence research: rather than replacing specialized models with monolithic LLMs, the most effective systems often combine the semantic breadth of foundation models with the behavioral precision of domain-specific architectures, using alignment techniques to make the two cooperate.

At the same time, the study is a reminder that integrating foundation models into high-stakes domains demands care. Educational diagnoses shape what students are asked to study next, and systematic errors could compound over a learner’s academic career. The Zhejiang University framework addresses this by grounding LLM judgments in the SOLO taxonomy, a structure validated by decades of educational research, and by requiring that semantic knowledge earn its place in the diagnosis model through rigorous alignment objectives rather than blind trust. The research was supported by the National Natural Science Foundation of China and the Zhejiang Province Leading Geese Plan, and the authors have made their findings openly accessible. As large language models continue to seep into every corner of educational technology, this work offers a technically rigorous template for how their knowledge can be harnessed responsibly, not as an oracle that replaces educational measurement, but as a well-aligned partner that strengthens it.

Subject of Research: Using large language models and the SOLO taxonomy to enhance cognitive diagnosis models in intelligent education systems

Article Title: LLM-Driven Cognitive Diagnosis with SOLO Taxonomy: A Model-Agnostic Framework

Article References: Dong, Z., Chen, J., & Wu, F. (2025). LLM-Driven Cognitive Diagnosis with SOLO Taxonomy: A Model-Agnostic Framework. Frontiers of Digital Education, 2(2), Article 20. https://doi.org/10.1007/s44366-025-0057-8

Image Credits: AI Generated

DOI: 10.1007/s44366-025-0057-8

Keywords: large language models, cognitive diagnosis, SOLO taxonomy, intelligent education, personalized learning, contrastive learning, mask-reconstruction learning, cold-start problem, knowledge representation, educational data mining, model-agnostic framework, Zhejiang University