Jul282025 by Sebastian GombertNo Comments
New Pub: TBA at BEA 2025 Shared Task: Transfer-Learning from DARE-TIES Merged Models for the Pedagogical Ability Assessment of LLM-Powered Math Tutors

New Pub: TBA at BEA 2025 Shared Task: Transfer-Learning from DARE-TIES Merged Models for the Pedagogical Ability Assessment of LLM-Powered Math Tutors

New Pub
In the BEA 2025 Shared Task on Pedagogical Ability Assessment of AI-Powered Tutors, the goal was to evaluate how well LLM-based math tutors support students. The task focused on four aspects of feedback: spotting mistakes identifying where the mistake happens giving guidance providing actionable suggestions For our submission, we built on FLAN-T5 models with a multi-step training pipeline. In addition to standard fine-tuning, we used model merging (DARE-TIES) to leverage information across all four labels – and saw clear improvements over plain fine-tuning. Our models achieved F1 scores between 52 and 69 and accuracies between 62% and 87%, ranking 11th, 8th, 11th, and 9th across the four tracks. Link to the paper: Link
Read More
Jul212025 by Heather WehnerNo Comments
New Pub: How Feedback Literacy Moderates Student Perceptions of Feedback

New Pub: How Feedback Literacy Moderates Student Perceptions of Feedback

Feedback, Higher Education, Journal, New Pub
Whether or not students receive effective feedback can have a big impact on their overall learning process. The more qualitative and personalized the feedback is, the more effective it is in supporting the students with their individual learning goals. The latest developments in learning analytics and artificial intelligence have made it possible to provide a large number of students with personalized feedback automatically and simultaneously. Despite these technical advances, there is still much to be learned about the ability of students to use this feedback for their scholastic benefit. So far, only a limited number of studies have examined the impact of feedback literacy on students' perceptions of feedback, which is particularly true for technology-enhanced learning environments. A newly published paper addresses this issue and focuses on how students interpret…
Read More