Date
AI Overview
Why it matters
High-quality feedback is essential for learning but is time-intensive for teachers. Automated feedback systems often lack curricular grounding, overlook partial reasoning, and provide limited avenues for educator control.
Study at a glance
- Question: How can a curriculum-grounded, modular AI feedback system support science assessment with educators in the loop?
- Setting and data: 30 participants with STEM teaching experience at high school or college levels, and 100 authentic student responses to a GCSE science question.
- Method: System development, technical benchmark evaluation against baseline models, and a user questionnaire.
- AI tools: LearnLens, Meta-Llama-3-8B-Instruct, Qwen2.5-32B-Instruct, QwQ-32B
Key findings
- LearnLens achieved higher scoring accuracy and a correlation of 0.388 on 100 student answers, outperforming baseline models while cutting latency compared to QwQ-32B.
- Across nine survey measures, 30 educators rated the system at 4.1 out of 5 or higher, reporting strong navigation ease, responsiveness, and scientific accuracy.
- Half of surveyed teachers previously spent 10 to 30 minutes grading per assignment, but median completion time dropped below 5 minutes using LearnLens.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
Effective feedback is essential for student learning but is time-intensive
for teachers. We present LearnLens, a modular, LLM-based system that generates
personalised, curriculum-aligned feedback in science education. LearnLens
comprises three components: (1) an error-aware assessment module that captures
nuanced reasoning errors; (2) a curriculum-grounded generation module that uses
a structured, topic-linked memory chain rather than traditional
similarity-based retrieval, improving relevance and reducing noise; and (3) an
educator-in-the-loop interface for customisation and oversight. LearnLens
addresses key challenges in existing systems, offering scalable, high-quality
feedback that empowers both teachers and students.
Research Categories
What is the application?
Who age?
Why use AI?
Methods
AI tools
Publication Source
Publisher
arXiv
