Jarne Thys

Jarne Thys

Ph.D. Researcher in Human-Centered AI for Education

Posts by Collection

portfolio

publications

INSIGHT: Bridging the Student-Teacher Gap in Times of Large Language Models

Published in D-SAIL Workshop - Transformative Curriculum Design: Digitalisation, Sustainability, and AI Literacy for 21st Century Learning, 2025

The rise of AI, especially Large Language Models, presents challenges and opportunities to integrate such technology into the classroom. AI has the potential to revolutionize education by helping teaching staff with various tasks, such as personalizing their teaching methods, but it also raises concerns, for example, about the degradation of student-teacher interactions and user privacy. This paper introduces INSIGHT, a proof of concept to combine various AI tools to assist teaching staff and students in the process of solving exercises. INSIGHT has a modular design that allows it to be integrated into various higher education courses. We analyze students' questions to an LLM by extracting keywords, which we use to dynamically build an FAQ from students' questions and provide new insights for the teaching staff to use for more personalized face-to-face support. Future work could build upon INSIGHT by using the collected data to provide adaptive learning and adjust content based on student progress and learning styles to offer a more interactive and inclusive learning experience.

Recommended citation: J. Thys, S. Vanbrabant, D. Vanacken, G. Rovelo Ruiz, INSIGHT: Bridging the student-teacher gap in times of large language models, in: Proceedings of the D-SAIL Workshop - Transformative Curriculum Design: Digitalisation, Sustainability, and AI Literacy for 21st Century Learning, CEUR-WS, Palermo, Italy, 2025, pp. 50-59.
Download Paper

Improving AI Text Classification: A Cascaded Approach

Published in 3rd Workshop on Engineering Interactive Systems Embedding AI Technologies, 2025

LLMs have rapidly evolved into versatile ''foundation models'', repurposed - despite persistent gaps in reliability - for a variety of tasks, such as legal document summarization, medical question answering, and text classification. In this paper, we propose an approach to engineer better text classification solutions for educational grading. We address this challenge with a solution that couples (i) a transformer cascade for rubric-level prediction with (ii) a transparent, traffic-light feedback interface powered by a Mixture-of-Agents LLM system. We compared our approach to a standard LLM and a single transformer architecture using the ASAG dataset. Results show that our approach increases recall for incorrect answers by more than 50% and precision on fully correct answers by 20% compared to a single transformer. Finally, we describe a prototype implementing our approach in an end-to-end, minimally intrusive solution for semi-automatic grading, which allows the teaching staff to review and revise the feedback generated by a Mixture-of-Agents LLM system based on the grade classification.

Recommended citation: Thys, Jarne; Vanacken, Davy & Rovelo Ruiz, Gustavo (2025) Improving AI Text Classification: A Cascaded Approach. In: 3rd Workshop on Engineering Interactive Systems Embedding AI Technologies, Trier, Germany, 2025, June 24.
Download Paper

The Effect of VR and Haptic Feedback Devices on Online Consumer Decision-Making

Published in Book of abstracts - 31st Recent Advances in Retailing & Consumer Science Conference, 2025

Recommended citation: DOUCE, Lieve; THYS, Jarne; VAN DE SANDEN, Stephanie; WILLEMS, Kim; VANACKEN, Davy & ROVELO RUIZ, Gustavo (2025) The Effect of VR and Haptic Feedback Devices on Online Consumer Decision-Making. In: Book of abstracts - 31st Recent Advances in Retailing & Consumer Science Conference.
Download Paper

Engineering Trustworthy Automation: Design Principles and Evaluation for AutoML Tools for Novices

Published in Engineering Interactive Computer Systems - EICS 2025 - International Workshops and Doctoral Consortium, 2025

AutoML systems targeting novices often prioritize algorithmic automation over usability, leaving gaps in users' understanding, trust, and end-to-end workflow support. To address these issues, we propose an abstract pipeline that covers data intake, guided configuration, training, evaluation, and inference. To examine the abstract pipeline, we report a user study where we assess trust, understandability, and UX of a prototype implementation. In a 24-participant study, all participants successfully built their own models, UEQ ratings were positive, yet experienced users reported higher trust and understanding than novices. Based on this study, we propose four design principles to improve the design of AutoML systems targeting novices: (P1) support first-model success to enhance user self-efficacy, (P2) provide explanations to help users form correct mental models and develop appropriate levels of reliance, (P3) provide abstractions and context-aware assistance to keep users in their zone of proximal development, and (P4) ensure predictability and safeguards to strengthen users' sense of control.

Recommended citation: Thys, J., Vanacken, D., & Rovelo Ruiz, G. (2025). Engineering Trustworthy Automation: Design Principles and Evaluation for AutoML Tools for Novices. arXiv preprint arXiv:2511.22352.
Download Paper

talks

Paper presentation: “Improving AI Text Classification: A Cascaded Approach”

Published:

LLMs have rapidly evolved into versatile “foundation models”, repurposed - despite persistent gaps in reliability - for a variety of tasks, such as legal document summarization, medical question answering, and text classification. In this paper, we propose an approach to engineer better text classification solutions for educational grading. We address this challenge with a solution that couples (i) a transformer cascade for rubric-level prediction with (ii) a transparent, traffic-light feedback interface powered by a Mixture-of-Agents LLM system. We compared our approach to a standard LLM and a single transformer architecture using the ASAG dataset. Results show that our approach increases recall for incorrect answers by more than 50% and precision on fully correct answers by 20% compared to a single transformer. Finally, we describe a prototype implementing our approach in an end-to-end, minimally intrusive solution for semi-automatic grading, which allows the teaching staff to review and revise the feedback generated by a Mixture-of-Agents LLM system based on the grade classification.

Paper presentation: “INSIGHT: Bridging the Student-Teacher Gap in Times of Large Language Models”

Published:

The rise of AI, especially Large Language Models, presents challenges and opportunities to integrate such technology into the classroom. AI has the potential to revolutionize education by helping teaching staff with various tasks, such as personalizing their teaching methods, but it also raises concerns, for example, about the degradation of student-teacher interactions and user privacy. This paper introduces INSIGHT, a proof of concept to combine various AI tools to assist teaching staff and students in the process of solving exercises. INSIGHT has a modular design that allows it to be integrated into various higher education courses. We analyze students’ questions to an LLM by extracting keywords, which we use to dynamically build an FAQ from students’ questions and provide new insights for the teaching staff to use for more personalized face-to-face support. Future work could build upon INSIGHT by using the collected data to provide adaptive learning and adjust content based on student progress and learning styles to offer a more interactive and inclusive learning experience.

teaching