KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Start date: 2025Subject: search.filters.subject.Generative AI

Search Results

Now showing 1 - 4 of 4
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    A Persona-based Automated Evaluation Framework for Intelligent AI Teaching Assistants
    (2026-06-16)
    Limcharoen, Chananyu
    ;
    Sripinta, Keetaphat
    ;
    Pasupa, Kitsuchart
    To address global teacher shortages and the need for personalized learning, we develop an intelligent teaching assistant leveraging multimodal large language models, agentic retrieval-augmented generation, and function calling. Unlike standard models, our system provides verifiable pedagogical guidance by reasoning across heterogeneous resources, including lecture slides and instructional videos. To overcome the scarcity of real-world datasets and high human evaluation costs, we propose a scalable, human-annotation-free framework utilizing simulated learner agents grounded in the Big Five personality theory. This allows for systematic assessment across 18 distinct student personas. We introduce a novel process-level metric, the dialogue recovery rate, and a dynamic adaptive policy to mitigate conversational deadlocks. Experimental results across 1,800 simulated dialogues using the Qwen3 family (8B, 14B, 32B) and its Thai-variant (Typhoon 2.5) reveal that Qwen3-14B attains the highest robustness and aggregate tutor-performance score within the proposed framework (72.6%). Analysis demonstrates significant correlations between learner traits and performance: Conscientiousness positively correlates with success (r = 0.49), while Extraversion is negatively associated with structural adherence (r = -0.54). This work establishes a reproducible benchmarking protocol for persona-aware, adaptive intelligent tutoring systems.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Integrating generative AI with the flipped classroom teaching model: enhancing emotional well-being and student achievement
    (2026-01-01)
    Liu, Hanchu
    ;
    Sriwisathiyakun, Kanyarat
    ;
    Petsangsri, Sirirat
    Education in the modern society is undergoing rapid transformation as helping students perform better academically and feel emotionally better has become increasingly important. One way to support this is by using Generative AI (GenAI) in combination with the flipped classroom approach. This study focused on creating and testing a new teaching model called the Generative AI-Integrated Flipped Classroom (GenAI-FC) designed for mental health courses. The research was done in two main parts. In the first part, the GenAI-FC model was developed and its structure was adjusted based on feedback from experts. In the second part, the model was used with students to see how it affected their learning and emotional well-being. The results were promising as five experts reviewed the model and gave it a high-quality score of 4.68 out of 5, showing that it was strong and useful for teaching. Then, the model was tested with 95 first-year university students. After using the model, students showed clear improvement in their exam scores and emotional well-being, based on a standard questionnaire. Both scores were significantly higher after the course compared to before as the results show that the GenAI-FC model can make a real difference by helping students to learn better and also feel more supported. This suggests that using Generative AI in a flipped classroom could be a helpful way to improve education and support students’ mental health at the same time.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Cognitive Offload Instruction with Generative AI: A Quasi-Experimental Study on Critical Thinking Gains in English Writing
    (2025-07-01)
    Hong, Hui
    ;
    Vate-U-Lan, Poonsri
    ;
    Viriyavejakul, Chantana
    This study explores the impact of generative AI-enabled cognitive offload instruction on the development of critical thinking skills in English essay writing among first-year university students. A quasi-experimental design was employed, comparing traditional instruction with an AI-augmented pedagogy that delegated lower-order writing tasks to generative AI tools, allowing students to focus on analysis, evaluation, and reflection. Over 12 weeks, 240 participants engaged in structured writing cycles involving AI brainstorming, individual critique, peer-AI co-revision, and reflective journaling. Results revealed that the AI-enabled cognitive offload group demonstrated significantly greater improvements in standardized critical thinking assessments and produced higher-quality essays in terms of logical coherence, evidence use, and originality. Mediation analysis indicated that cognitive offloading behavior partially explained the relationship between AI use and critical thinking gains. The findings suggest that when generative AI is integrated into pedagogy through deliberate scaffolding, it can enhance rather than hinder higher-order thinking. This study highlights the importance of balancing technological efficiency with instructional strategies that promote active engagement, metacognitive reflection, and collaborative learning. It offers practical implications for educators seeking to incorporate AI tools without compromising the development of essential cognitive skills, proposing that structured cognitive offload instruction can serve as an effective approach to fostering critical thinking in second-language writing contexts.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Generative AI–mediated scaffolds for enhanced critical thinking in EFL writing
    (2025-01-01)
    Hong, Hui
    ;
    Vate-U-lan, Poonsri
    ;
    Viriyavejakul, Chantana
    Generative AI tools present new opportunities for enhancing critical thinking (CT) in English as a Foreign Language (EFL) writing instruction. This study investigates how the structured integration of these technologies could support the development of CT skills, particularly in vocational education contexts. An eight-week multiple-case action research design was conducted across three vocational colleges, involving 92 students engaged in iterative writing and revision cycles guided by the GenAI-CT framework. This pedagogical model draws on Bloom’s taxonomy, Vygotsky’s Zone of Proximal Development, and cognitive apprenticeship theory to scaffold learners through increasingly complex reasoning tasks. Data were collected from student essays, AI interaction logs, reflective journals, and classroom observations. Mixed-methods analysis revealed statistically significant gains across all CT dimensions (p<.001). Thematic findings indicated notable increases in analytical depth, metacognitive reflection, and evaluative judgment. Variations across cases underscored the influence of disciplinary focus and instructional mediation styles. These results demonstrate that generative AI, when embedded in intentional pedagogical structures, can foster cognitive engagement rather than superficial automation. The GenAI-CT framework offers a replicable model for integrating AI in applied language and communication instruction, supporting educators in cultivating critical thinking through technology-enhanced learning environments.