Papers for
education technology developers
Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.
Chinese essay correction from images needs better AI grounding
From Images to Grounded Edits: A Real-World Benchmark for Chinese Grammatical Error Correction in Handwritten Essays
Abstract: Chinese Grammatical Error Correction (CGEC) is typically formulated as a text-to-text problem. While suitable for digital texts, this formulation falls short in real-world K-12 education, where AI-assisted corrections are expected directly on essay images, which are primarily handwritten and exhibit many irregularities. To bridge this gap, we introduce Grounded Chinese Grammatical Error Correction (G-CGEC), an image-to-grounded-edit task requiring systems to predict both corrections and their positions on essay images. We propose G-CGEC-Eval, a benchmark comprising real-world images of K-12 Chinese essays with fine-grained annotations. For evaluation, we adapt IoU-based metrics from object detection and propose a more tolerant alternative based on center-distance matching. Using this benchmark, we evaluate open-source and proprietary vision-language models under a direct single-pass setting, as well as settings with auxiliary components (OCR and character grounding) coordinated via pipelining or agentic harnessing. Results show that even top-tier proprietary models perform surprisingly poorly in the single-pass setting, while pipelining and agentic harnessing yield meaningful improvements. Notably, an error-type-based multi-agent workflow achieves the best performance, establishing it as the strongest baseline for future G-CGEC research. Through ablations and fine-grained analysis, we find the task remains far from solved, with linguistic error discovery and character-level grounding as the primary bottlenecks. This underscores the need for models that better integrate visual perception with linguistic reasoning and visual grounding.
Ai chatbot links student reasoning with essay revision improvements
Thinking Is Not Writing: Designing AI Chatbots to Connect Reasoning and Revision
Abstract: Supporting students' argumentative writing with AI requires connecting reflection to their revision processes. We present Maike, a Socratic chatbot supporting writing through argument diagnosis, targeted questioning, and a student model across Think and Write modes. In a classroom study, 65 secondary-school students used Maike or a control chatbot sharing the interface, language model, and Think/Write modes. Approximately 40% of students improved their essay scores. However, Maike users engaged more in idea-level dialogue (56% vs. 44%) and moved iteratively between discussion and editing. Transitions from ideas discussed in dialogue to revisions were positively associated with score gains. These findings suggest a design target for AI writing support: coordinating reflection with revision. We contribute an architecture for supporting argumentative reasoning without generating essay text and an approach linking interaction patterns to writing processes and outcomes. As AI becomes embedded in classrooms, understanding these connections is essential to assessing (and designing for) its educational value.
Classquest helps teachers identify topics needing reteaching from quizzes
From Source-Based Quizzes to Reteaching Decisions: A Practitioner Guide to ClassQuest
Abstract: A source-based quiz can help a computing teacher identify material to explain again, but its report must preserve the limits of the evidence behind that decision. We present ClassQuest, a prototype connecting teacher-reviewed question drafts, private student responses, topic reports and targeted retries. A Year 10 classroom account of an earlier prototype supplies 20 usefulness ratings from 24 invitees, with a mean of 8.0 and median of 9 on a ten-point scale. A Boolean-logic episode documents how immediate feedback, a teacher explanation and a fresh question were combined. We separate this account from a completed technical audit and reusable teaching guide. An exhaustive single-item audit found no count mismatches across 5,456 constructed response configurations, while diagnostic cases exposed a retry increase caused entirely by changing participation and a progression suggestion based on one learner's three answers. A further case shows that an unoffered retry can be labelled missing. A separate reporting companion distinguishes opportunity to respond, pending review and matched retry cohorts. Its completion-sensitivity check matched an independent oracle in 46,375 constructed states across roster sizes 1-30, identifying when unknown responses can change a reporting band. Our contributions are a source-linked formative workflow, executable examples of interpretation failures, and reporting and teaching materials for examining those failures. Neither the questionnaire nor the audit establishes improved learning; the findings identify reporting requirements and practical directions for formative teaching.
Multi-agent reasoning improves solutions by training at test time
Consolidating Reasoning with Test-Time Training
Abstract: Effective multi-agent collaboration requires finalizing solutions from reasoning that is distributed across the individual attempts of many agents. However, useful intermediate reasoning can remain unexploited when collaboration is limited to voting on conclusions reached among individual agents, or aggregating long, noisy collections of reasoning trajectories in context. In this work, we propose TTT-Consolidate, a framework that uses multi-agent reasoning trajectories as adaptation data to improve a model's subsequent reasoning. TTT-Consolidate jointly consolidates trajectories into parametric representations through test-time training, then generates a new solution by conditioning on the consolidated information. We meta-learn how to consolidate using bi-level optimization at training time, where an inner loop encodes reasoning trajectories into a lightweight LoRA adapter, and an outer loop learns meta-parameters for the inner loop such that the consolidation is helpful for the model to synthesize a final solution. As no large-scale corpus of diverse reasoning trajectories exists for training aggregation methods, we construct the OpenParallelThinking corpus composed of 12,810 math problems paired with a mixture of trajectories from six LLMs. Evaluated on challenging math and STEM benchmarks, TTT-Consolidate outperforms the best aggregation baselines by up to 20 percentage points, even under matched compute and runtime settings, with the gap widening at larger model scales. TTT-Consolidate also recovers from unsuccessful individual trajectories more robustly, an ability that improves as the number of available (even incorrect) trajectories increases. Finally, we demonstrate that TTT-Consolidate benefits from both SFT and RL-based outer loop objectives. We will release TTT-Consolidate and OpenParallelThinking for use in future work on reasoning aggregation.
Text indexing improves zero-shot knowledge tracing across platforms
Text as an Index for Zero-Shot Cross-Domain Knowledge Tracing
Abstract: Knowledge tracing (KT) predicts a student's next response from their history. New platforms often have question texts but no response logs for training, motivating zero-shot cross-domain KT. Existing transfer and cold-start methods use question semantics, but cross-platform semantic discrepancies limit transferability. We propose TIZSKT, which separates behavioral sequence modeling from domain-local historical evidence construction and uses text as an index rather than a directly transferable predictive representation. The Mastery-Dynamics Encoder learns correctness dynamics without question identifiers or text embeddings. Domain-Local Question Addressing builds fixed question addresses using a frozen text encoder and an unsupervised per-domain projection. The Text-Addressing Kernel uses these addresses to aggregate the current student's previous outcomes into a question-specific historical correctness summary. Cross-Segment Continuation retains access to earlier responses without extending the behavioral encoder's input sequence. Evidence-Volume Read-Out preserves the total kernel mass discarded by normalization and combines its log-compressed value with the behavioral state and historical correctness summary to predict the next response. All trainable parameters are learned from source domains; target inference uses public question texts and the current student's observed history without target-domain training. Leave-one-domain-out experiments on three public datasets show that TIZSKT achieves the highest mean AUC and accuracy among evaluated baselines on all target domains. Ablations confirm the contributions of text addressing and cross-segment continuation.
EdU-Jev improves automated education decisions with faster accurate models
EDU-Jev Training System-One Decision Models for Education
Abstract: Many automated decisions in education involve choosing from a fixed set of options: assigning a rubric score, checking whether an answer meets a marking criterion, or identifying the first wrong step in a solution. Generative language models are increasingly used to make these decisions, but their responses require parsing, longer outputs increase inference costs, and confidence expressed in words does not necessarily reflect the probability of being correct. We present EDU-Jev, a family of single-pass ("System One") decision models at 0.8B, 2B and 4B parameters. Given an assessment context and a question with predefined answer options, the model returns a probability distribution over those options without generating text. A pointer head scores a marker for each option, ensuring the predictions are restricted to the allowed choices. Training uses a single supervised stage with soft cross-entropy against the available target label distributions; calibration is assessed empirically. Across twelve education benchmarks, EDU-Jev 4B achieves an average accuracy of 67.6%, exceeding the strongest of five commercial decision APIs by 9.4 percentage points and the best open 4B decision model by 18.7 points. On four cross-domain education sets, it matches the strongest API, which remains ahead on general decision-making and reasoning tasks. The 2B model processes about 150 decisions per second on a single H100 GPU.
Dense retrieval improves with constraint-aware hard negative mining
CA-HNM: Constraint-Aware Hard Negative Mining for Dense Retrieval with Structured Domain Models
Abstract: Dense retrievers are commonly trained with hard negatives selected from lexical or dense retrieval results. Retrieval proximity, however, does not indicate whether a candidate conflicts with explicit domain structure. We introduce CA-HNM, a constraint-aware hard-negative mining framework that combines retrieval-based candidate generation with deterministic incompatibility rules derived from a structured domain model. The framework removes known positives, constructs a local typed context around the query target, records relational, scope, target, and level mismatches, and uses the resulting candidates to fine-tune a standard dual encoder. Structured information is required only during offline negative construction. We evaluate CA-HNM on MOOCCubeX and Course-Skill Atlas with two encoders, two training losses, and ten seeds. Relative to a retrieval-rank-matched control, CA-HNM-Pure has higher mean NDCG@10 in six of eight dataset--encoder--loss configurations. Four hierarchical 95% bootstrap intervals are entirely above zero, mostly under triplet loss. In a separate experiment, CA-HNM-Mixed shows slightly higher mean NDCG@10 than a matched-mixed control on both collections. Structural variants show that changes in available structure can also change candidate eligibility and negative-pool composition. The results indicate that the contribution of constraint-aware selection depends on the training objective and the composition of the negative pool.
Multi-agent system improves feedback from online class videos
MAVE: A Multi-Agent Framework for Grounded Pedagogical Feedback from Online Class Videos
Abstract: Timely pedagogical feedback is difficult to scale in online classes, where long and noisy videos make student responses hard to locate and automated systems often produce generic advice weakly grounded in actual classroom behavior. The key challenge is to connect the instructional goal of a specific lesson segment with temporally aligned multimodal evidence of student responses, and then translate the observed gap into an actionable teaching move. We introduce MAVE (Multi-Agents for Video-based Educational Feedback), a multi-agent framework for grounded pedagogical feedback from online-class videos. MAVE decomposes feedback generation into four roles: the Curator structures the lesson and infers expected student activity; the Observer extracts aligned speech, visual, and interaction evidence; the Assessor estimates the activity supported by student behavior; and the Advisor generates gap-conditioned teaching recommendations. To evaluate this capability, we introduce MAVEBench, a benchmark designed to measure whether feedback systems can ground diagnoses in multimodal student evidence, and generate actionable pedagogical feedback. MAVEBench contains 173 knowledge-point segments from approximately 20 hours of authentic online-class videos across STEM and Humanities, together with comprehensive simulation. Experiments show that MAVE outperforms direct prompting, Reflexion, and TextGrad in diagnostic correctness, instructional alignment, and actionability. Our code is available at https://github.com/DaRL-GenAI/MAVE
Ai tutor answers computing questions in foreign languages with glossary help
Multi-sourced AI Tutor for Non-Native English Speaker Students
Abstract: Large language models (LLMs) are increasingly being adopted as teaching tools in computing education, particularly for developing AI tutors capable of answering student questions. With the rise in enrollment of international students in computing programs, researchers have begun to explore the difficulties that non-native English speaker (NNES) students face in computing courses due to language barriers. To aid such students, we developed a general-purpose AI tutor system that can process student questions in foreign languages (currently focused on Mandarin) and provide bilingual responses. Our system also incorporates the functionality of generating a glossary of technical terms and their explanations to enhance comprehension. Our approach utilizes a specialized Retrieval-Augmented Generation (RAG) pipeline with a novel question extraction mechanism, enabling us to effectively utilize a diverse array of course materials for answering student queries. We evaluated our AI tutor using 91 Piazza posts, demonstrating that it could answer 83.52% of the posts correctly and in a helpful manner. The tutor also provided high-quality translations for 76.92% of the questions and generated technical term glossaries for 64.47% of them. Our findings underscore the potential of multi-source RAG pipeline in enhancing AI tutor systems, offering support for non-native speakers that are challenging to provide with traditional supporting staff of a computing course.
Agreement between humans and ai graders varies by model prompt and university
Machine--human agreement in marking undergraduate assignments is specific to model, prompt and institution
Abstract: Large language models (LLMs) promise to automate one of higher education's most resource-intensive activities: assessing student writing. Existing evaluations are typically limited to a single model, a single prompt and a single institution. Using 761 undergraduate psychology assignments from three UK universities, we evaluated three frontier LLMs, individually and in ensemble, on accuracy, prompt sensitivity, error independence, generalisability and evidential basis. Agreement between human and machine marks varied widely, with no model or prompt optimal across institutions. All models compressed marks towards a common central tendency, overvaluing the weakest assignments and undervaluing the strongest. Because this error was shared, ensembling failed to remove it. Machine marks also rewarded linguistic features more strongly than human marks. Since human-machine agreement was a joint product of model, prompt and institution, we conclude that current LLMs lack evaluative capacity transferable across contexts, and that single-context validation overstates readiness for deployment.
LLM tutors can improve learning but require careful setup
Do LLM Tutors Actually Teach? A Process-Centered Synthesis of the Tutoring Loop
Abstract: Large language models can produce fluent tu- toring dialogue, but whether they actually help students learn remains unclear. We present a process-centered synthesis of LLM tutoring that follows the path from learner-state infer- ence to pedagogical action, tutor training, eval- uation, and student simulation. This view ex- poses a central gap: implementing a tutoring component does not establish that it works or that its outputs meaningfully affect later stages. A structured study-level audit shows that peda- gogical evaluation is common, while evidence becomes much thinner for learner-conditioned intervention, human learning gains, and espe- cially transfer or delayed retention. Human studies nevertheless provide a conditional posi- tive result: LLM tutors can improve learning, but benefits depend on pedagogical structure, learner engagement, and how learning is mea- sured. We argue that progress requires validat- ing the interfaces between tutoring stages, not only improving individual components.
Using AI partners before class boosts student discussion participation
How assigned AI use before class shapes active student engagement in class
Abstract: AI learning tools are rapidly entering classrooms, but evidence about whether they help students learn is mixed and rests mostly on test scores. Comparatively less research addresses whether the use of AI changes students' live learning behaviors in class. Here, we report the results of a preregistered field experiment with 759 MBA students enrolled in ten sections of a course, in which each student was randomly assigned two of ten class sessions to prepare for with a purpose-built voice-based AI discussion partner. After two uses of the AI discussion partner, students made about 31% more voluntary contributions in each later class session. Students who used the AI discussion partner more also reported greater comfort speaking up and greater perceived learning, but not greater focus or motivation. These findings suggest that repeated practice with a voice-based AI partner can meaningfully increase students' engagement in class discussion, enhancing a critical intermediate learning outcome.
Reinforcement learning model creates efficient expert learning paths
EVOL: Simulator-Guided Evolutionary Expert Synthesis for Deployment-Free Learning Path Recommendation
Abstract: Reinforcement learning (RL) for learning path recommendation (LPR) faces two coupled obstacles. First, the policy must commit to a sequence of L concepts without intermediate feedback, producing a combinatorial search space that grows super-exponentially with L and provides reward only at the final step. Second, expert learning paths would be the natural cure for sparse-reward RL, but they do not exist in educational data, because student logs record what learners did, not what they should have done. We address both obstacles by importing a recipe from simulator-based demonstration learning in robotics: the knowledge tracing simulator is used both to synthesize per-learner expert demonstrations through evolutionary search and to train a deployment-free policy that distills these demonstrations into a feed-forward learner. Our framework, EVOL, instantiates this pipeline with an asymmetric actor-critic where the actor commits to deployment-realistic blind planning while the critic exploits the privileged simulator state during training. Across three datasets (ASSIST15, Junyi, and EdNet; 39-189 concepts) and path lengths L = 5, 10, and 20, EVOL surpasses 8 baselines spanning heuristic, sequential, RL, graph-enhanced RL, and LLM-enhanced methods. We further compare three imitation strategies (BC, AWR, and DAPG) and show that final performance is governed by the quality of evolutionary experts rather than by the particular imitation objective.
Desk robot projects AI help next to handwritten work boosting learning
AIfred: Augmented Learning through Functional Robotic Embodiment at the Desk
Abstract: Desk-based learning and creative activities benefit from handwritten engagement. However, current generative AI tools deliver guidance through a separate screen, creating a gap between where users think and where assistance appears. To address this, in this work we design AIfred, a desk-based robotic arm with a projector mounted at the end-effector that places AI-generated guidance alongside handwritten work. AIfred combines workspace perception, context-aware content generation, and robot-mediated projection to support math assignments, image generation, and drawing tasks. In a user study (n = 36), we compared AIfred against ChatGPT (GPT-5.6 Luna) running on a laptop. Both tools performed comparably while assistance was available during the math assignment (6.7 vs. 7.3/10, p = .41), but AIfred improved short-term learning transfer by 60% once assistance was withdrawn (7.0 vs. 4.4/10, p = .003). In addition, independent art and design professors ranked drawings produced with AIfred better in 33 of 36 cases. Our findings indicate that spatially co-located AI assistance benefits tasks whose guidance shares a spatial frame with the work.
Generative AI helps improve learning but not critical thinking skills
Critical Thinking with Generative AI: A Constraint-First Design Pilot of a Thinking-Partner Intervention
Abstract: Generative AI (GenAI) tools entered higher education classrooms faster than the field was able to study their effects on learning. One concern is that GenAI may displace the critical thinking and AI literacy that students will need after graduation. This paper reports a Design-Based Research pilot of a GenAI-assisted critical thinking framework, in which ChatGPT was used as a thinking partner in an undergraduate research methods and statistics course during Spring 2025 (N = 14). The mixed-methods design combined pre- and post-intervention measures of statistical learning (AASCDM), AI literacy (MAILS), and critical thinking (WGCTA) with instructor field notes, student artifacts, and student-AI interaction logs. Pre-post tests showed gains on every AASCDM dimension and on eight of nine MAILS dimensions, while WGCTA percentiles did not change. Qualitative analysis identified four themes: the ways students positioned the LLM (as answer generator, validator, or co-thinker); the depth of student engagement (procedural vs. conceptual); occasional humanizing of the tool; and the role of curriculum design in shaping each of the prior three. Read together, the findings indicate that one semester of GenAI-assisted instruction can move domain learning and self-reported AI literacy but does not move standardized critical thinking, and that the modal student-LLM relationship is one of validation instead of dialogue. We end with design principles for the next iteration of the framework and implications for research on adaptive and personalized learning.
Students find tablets helpful for stepwise math learning but mixed overall
Student Perceptions of Tablet-Based Teaching and Learning in TNE Undergraduate Mathematics
Abstract: Tablet-based teaching and learning has become increasingly common in university mathematics courses, offering capabilities such as digital ink, dynamic visualisation, and real-time annotation. However, there is limited experiential evidence regarding how students perceive the specific benefits and drawbacks of tablet-supported teaching and learning, particularly in Transnational Education (TNE) settings. This paper presents results from a small-scale exploratory survey of undergraduate students ($n = 19$) attending mathematics courses within an applied sciences degree programme, who anonymously rated a set of statements regarding their experiences with tablet-based instruction on a five-point Likert scale. Initial analysis shows that students in this cohort perceived tablet teaching most positively in supporting step-by-step understanding and active engagement during lectures through real-time annotation and structured note-taking. In contrast, perceptions related to long-term recall, interest in mathematics, and preference over alternative teaching methods were more mixed. These findings suggest that students in this cohort perceived tablet-based teaching positively for supporting procedural understanding, while perceptions of other aspects of learning appeared more varied.
First generation low income students use limited large language model tools
Accessible, but Not Adopted: Increasing LLM Adoption among First-generation, Low-income (FGLI) College Students beyond Expanding Access
Abstract: Large language models (LLMs) are increasingly positioned as a force to empower underserved communities, and significant efforts are being made to expand access. Yet, access alone does not equate to meaningful adoption. First, even if a system is accessible, it won't be adopted if users are not willing to adopt it. Second, even if an LLM system is superficially adopted, the heterogeneity of LLM tools means that LLM adoption can be further deepened. Closing this access-adoption gap is critical to ensuring that the full social potential of LLM is not only accessible but fully realised. Drawing on 61 interviews (15 long-form semi-structured interviews with first-generation, low-income college (FGLI) students, 3 non-FGLI students, 3 FGLI program directors, and 40 intercept interviews), this paper examines the access-adoption gap in first-generation, low-income student communities. This paper a) finds that while FGLI students have adopted LLM systems, their depth of LLM tool usage is limited to chatbots (e.g., ChatGPT or Claude) for narrow use cases, and b) identifies barriers limiting their willingness to learn and use (low perceived value, under-estimated self-efficacy, unclear starting point, low peer exposure, and resource constraints). Then, from these findings, the paper derives the four design principles to design a system or an intervention aimed at closing the access-adoption gap in LLM adoption by FGLI students. In doing so, the paper contributes to the field by a) examining the LLM access-adoption gap in the FGLI student community, and b) reframing LLM adoption as a depth gradient across four modes of LLM tool use: basic chatbot interfaces, tool-augmented prebuilt interfaces, agentic development interfaces, and programmatic integration.
Elementary teachers adapt practices for AI in classroom curriculum
Adapting for AI: How elementary teachers adjust their practices for an AI-integrated curriculum
Abstract: Conversational AI tools are entering children's everyday experiences, and schools are interested in adopting them. However, successful classroom integration depends not only on the technology but also on the work teachers do to make it usable and appropriate for their students and classroom context. There is little known about how elementary teachers work as they implement conversational AI tools in real classrooms. In this study, we examine three teachers' experiences implementing an AI literacy and English Language Arts (ELA) curriculum built around ToyTalk, a conversational AI toy development platform, over 13 instructional days, a three-week summer camp. Drawing on daily individual reflections, group reflections, and post-camp interviews, we find that teachers' adaptive practices of repair, differentiation, translation, and balancing sit at the intersection of three tensions (technology, learner, and instruction). Teachers' understanding of AI and their role evolved over the camp experiences. From these findings, we contribute design implications and considerations for deploying conversational AI within elementary classrooms.
DeepEdu improves speed and accuracy of Vietnamese AI tutoring systems
DeepEdu-v1: Efficient and Scalable Agentic LLMs for Vietnamese Education
Abstract: AI tutoring could markedly improve learning outcomes for students in developing regions such as Vietnam, yet the two obvious paths both fall short. Cloud assistants such as ChatGPT route sensitive student data to foreign servers---violating data-sovereignty laws such as Vietnam's Decree 53---and, pre-trained on Western-centric corpora, are not organized around the national textbook curriculum, so their knowledge of local content is unsystematic and frequently hallucinated. Self-hosting an open model keeps data on-premise but hits a two-fold wall: post-training quantization (AWQ, GPTQ) tames the static weight footprint, yet the dynamic KV cache and prefill latency of long tutoring contexts still cause out-of-memory failures and slow responses on consumer GPUs, while the model keeps hallucinating on region-specific material. We present DeepEdu-v1, an AI-tutoring system for Vietnamese education built on SCALE (Self-improving Context-Aware Learning Engine), a framework with two innovations. First, a long-context inference engine amortizes token selection from per-sub-chunk to per-cluster granularity; on long-context retrieval it issues x7.7 fewer retrieval calls than a state-of-the-art selective-attention baseline, cutting prefill latency (TTFT) by roughly 35% while matching or improving task accuracy. Second, a self-improving agentic layer continuously curates a verified playbook from past interactions instead of fine-tuning, a design intended to progressively reduce reliance on dominant-language priors as trustworthy local knowledge accumulates. In its deployed configuration, DeepEdu achieves a nearly x2 TTFT speedup over standard vLLM serving and lifts agentic accuracy from 70.0% to 79.5% on complex tasks, with the strongest per-track gains across financial-reasoning and interactive-agent benchmarks.
AI tutors match human experts in GRE learning gains at low cost
StudentBench: AI and human tutoring yield equivalent GRE learning gains
Abstract: Artificial intelligence offers an unprecedented opportunity to augment human capabilities, yet progress at the frontier has focused primarily on advancing model capabilities. We introduce StudentBench, a suite of AI teaching evaluations and a public platform that enables large-scale data collection with over 175,000 student-AI messages to study whether large language models (LLMs) produce learning gains equivalent to human tutoring. Using StudentBench, we measured learning gains on Quantitative and Verbal GRE questions across 2,383 human participants receiving AI tutoring, human tutoring, or no tutoring. We establish that AI tutoring is statistically equivalent to expert human tutoring for GRE learning gains (p = .015), and in five of the seven GRE domains, the best performing AI tutor surpassed the human tutor, on average. In a second study, expert human tutors compared LLM-generated lesson plans and practice problems through 2,028 pairwise rubric evaluations. Together, the two studies clearly separate AI tutors across: (1) lesson planning, (2) practice-problem creation, (3) conversational pedagogy, (4) cost, and (5) engagement. Surprisingly, one AI tutor achieved learning gains equivalent to human tutoring (p = .044) at 918 times lower cost (USD 0.0052 for AI versus USD 4.81 for human, per percentage point gained). For Quantitative GRE sessions, faster AI replies correlated with more student messages, more messages with more correct practice, and more correct practice with larger learning gains (all p < .002). The StudentBench platform is freely available at https://studentbench.org.
Student use of generative AI varies with learning benefits and challenges
The Uneven Impact of Generative AI on Student Learning: Examining the Roles of Reliance, Evaluation Literacy, and Course Policy in AI-related Courses
Abstract: Generative artificial intelligence (GenAI) is changing how students learn, yet the roles of course context, cognitive reliance, evaluation literacy, and early reliance remain underexplored. Using survey responses from 118 students across 12 AI-related courses at our institution, we examined differences in GenAI use and perceived learning experiences. We identified four user clusters: high-use students reporting many benefits, light users reporting less reliance and fewer benefits, and two moderate-use groups reporting different levels of benefit. We also found significant differences between free- and premium-version users, single- and multiple-tool users, and students experiencing different instructor policies. In multivariable regression models, academic benefit was associated with early reliance and academic task support; positive impact was associated with cognitive reliance, academic task support, confidence in GenAI reliability, and instructor policy; and negative impact was associated with early reliance and attitudinal change. The association between early reliance and negative impact became stronger as evaluation literacy increased. Finally, perceptions of GenAI-enhanced learning appear to reflect cognitive, performance, and self-efficacy benefits, while concerns about stress and diminished critical thinking are associated with lower perceived learning benefits. These findings suggest that institutions need better policies to address such inequities so that institutions can enable students to benefit from increasingly capable AI systems.
Large language models show bias when assessing students with different backgrounds
The Role of Implicit and Explicit Demographic Signals in Large Language Model-based Student Assessment
Abstract: Large Language Models are now common in student assessment, but we know little about how student demographics affect their use. Sometimes, considering student demographics may be necessary -- for example, to improve readability for users with lower educational levels. However, it also risks being a cause of discrimination, e.g., when assigning lower scores to students from lower socioeconomic backgrounds. We set up controlled prompts to test 1) explicit demographic effects, where we mention demographic details directly, and 2) implicit effects, where we use conversation history as a demographic signal. We test these settings in three tasks: Automated Essay Scoring, Formative Feedback, and Metalinguistic Question Answering. We test six state-of-the-art LLMs on these tasks. In both explicit and implicit cases, the models pick up on demographic cues and can change their scoring, feedback, and answers accordingly. We find that LLMs frequently adjust the readability of feedback to education levels when these are explicitly mentioned. On the other hand, implicit conditions produce unpredictable biases, such as in question answering, where responses from lower-education levels receive lower sentiment scores. Our results provide clear evidence of demographic sensitivity in LLMs for educational assessment tasks.
AI tutoring platform shows promising gains in science exam scores
Evaluating AI Tutoring at the Speed of Innovation: Practitioner-Led Micro-Randomised Trials of an AI Tutoring Platform in GCSE Science
Abstract: Artificial intelligence (AI) systems in education are developing on timescales that sit uneasily with conventional evaluation. By the time a large-scale trial has been designed, delivered, analysed and published, the technology under study may have changed materially. This creates a temporal problem for evidence-informed education: the need for timely evidence can encourage reliance on weak observational or usage data, while conventional rigorous evaluation may produce evidence too slowly to guide rapidly evolving practice. We examine teacher-led micro-randomised controlled trials (micro-RCTs) as one response to this problem. The empirical case is a four-week multisite individually randomised evaluation of Medly, an AI-powered tutoring platform, in GCSE Biology, Chemistry and Physics in English secondary schools. Of 929 students completing baseline assessment, 644 completed post-testing. In the primary ITT analysis, students allocated to Medly achieved higher post-test attainment than students undertaking business-as-usual self-directed revision (Hedges' g = 0.33, 95% CI 0.18 to 0.48). Positive estimates were observed in Physics (g = 0.31), Chemistry (g = 0.32) and Biology (g = 0.52), with no evidence of differential impact by disadvantage status. Greater platform engagement was associated with higher attainment, but these post-randomisation analyses are treated as exploratory rather than causal. Attrition was substantial (30.7%), outcome measures were curriculum-aligned rather than standardised, and process evaluation response was limited. We therefore interpret the findings as preliminary. We argue that the value of micro-RCTs for educational AI lies not in replacing definitive evaluation with small studies, but in enabling a rapid, cumulative evaluation architecture in which randomised estimates can be generated, replicated and updated as technologies and their implementation evolve.
Vision language models improve handwritten exam grading accuracy and reliability
Vision-Language Models for Criterion-Level Grading of Handwritten Examinations in Outcome-Based Education
Abstract: Criterion-level grading connects examination performance to learning outcomes, but manual marking introduces workload and variation between markers. This study evaluates vision-language models (VLMs) for handwritten outcome-based assessment across five dimensions: accuracy, human agreement, repeated-run reliability, error concentration, and explanation quality. Using 1,982 criterion-level records from 485 undergraduate examination answers, we compare 20 configurations spanning Qwen2.5-VL, InternVL3, Pixtral, a Donut baseline, and a cascade ensemble. Evaluation setups include zero-shot prompting, few-shot prompting, partial fine-tuning, and Low-Rank Adaptation (LoRA). Two independent faculty markers regraded all 291 test criteria, providing a human agreement baseline on the same assessment materials. Qwen2.5-VL with LoRA achieved Quadratic Weighted Kappa (QWK) of 0.727 and mean absolute error of 0.435 marks against the examiner, compared with mean human-pair QWK of 0.551. This comparison reflects calibration to the examiner's training marks. LoRA outperformed partial fine-tuning for all three instruction-tuned VLMs, while few-shot prompting reduced QWK in every configuration with valid prompted scores. Aggregate reliability and exact repeatability diverged: intraclass correlations ranged from 0.790 to 0.874, yet 50.2-63.6% of criteria changed marks across five sampled runs. Attention-guided deletion showed no statistically significant advantage over random masking, and four faculty reviewers reached no consensus on explanation usefulness. These findings highlight the need for rubric-specific calibration, repeatable scoring, review of consequential errors, and separate validation of explanations. The released evaluation protocol supports criterion-level assessment research and grading tools with teacher oversight.