Program
Schedule Overview
Morning
| Time | Session | Description |
|---|---|---|
| 09:30 | Welcome and Introduction | Introduction to the workshop, including defining shared terms, an overview of current work, and emerging challenges of evaluating the pedagogical quality of automated feedback. |
| 09:45 | Interactive Session | Attendees evaluate real-world examples of automated feedback from various disciplines in small groups (K-12 English and mathematics, higher education mathematics, mechanical engineering, and other STEM subjects). |
| 10:15 | Coffee Break | |
| 10:30 | Lightning Talks | Short 5-minute presentations from participants on their submitted work. 1. A Combined Strategy for the Pedagogical Evaluation of Automated Feedback: Generation, Decision and Fairness — Kirouchenassamy et al. [PDF] 2. Beyond Surface Human-Likeness: AI–Mentor Feedback Alignment, Pedagogical Adaptation, and Student Engagement in Longitudinal Learning Data — Fan et al. [PDF] 3. Evaluating and Interpreting Gender Bias in LLM Feedback: Span-Level Embedding-Based Evidence from Automated Essay Feedback — Du et al. [PDF] 4. Evaluating the Pedagogical Quality of LLM-Generated Feedback: A Criterion-Based and Comparative Study — Kolle et al. [PDF] 5. Revision-Loop Behavior and Learning Outcomes under Voluntary AI Formative Feedback in an Undergraduate Statistics Course — Han [PDF] 6. Supporting Tutors in the Gig Economy with Automated Feedback: A Case Study on Ringle — Park et al. [PDF] 7. The Correct Answer Trap: Pedagogically-Grounded Detection and Feedback for Hidden Misconceptions — Imran & Bulathwela [PDF] 8. Using a Learning Progression Framework to Guide LLM-Based Formative Assessment in STEM Education — Wang et al. [PDF] 9. Does Caring Cost Precision? Evaluating Anxiety-Framed LLM Misconception Feedback for Undergraduate Mathematics — La Hadi et al. [PDF] See Accepted Papers for full abstracts and author affiliations. |
| 11:30 | Presenter Stalls | Attendees move freely between presenter tables for in-depth discussion of each submitted work. |
| 12:15 | Morning Summary | Organisers summarise key elements of the lightning talks, discussion, and interactive sessions, and introduce the afternoon themes. |
| 12:30 | Lunch |
Afternoon
| Time | Session | Description |
|---|---|---|
| 13:30 | Afternoon Opening | Organisers frame the afternoon and present the 4–6 themes identified during the Morning Summary. Participants self-select into cross-domain groups. |
| 13:45 | Part 1: Finding the Problems | Groups work through structured prompts to identify and articulate the key problems in evaluating automated feedback in their domains, using flip-chart paper and post-its. |
| 15:15 | Coffee Break | |
| 15:30 | Part 2: Exploring the Problems | Groups move from problem identification to research-ready framings, working through prompts on stakeholders, relevant theory, research questions, and open blockers. |
| 16:30 | Open Discussion | Dot voting across all groups’ outputs, followed by a facilitated whole-room conversation surfacing connections and themes across the afternoon’s work. |
| 16:45 | Closing | Organisers summarise the day’s outputs, introduce the ongoing communication channel, and frame the workshop write-up. |