LearnLens: LLM-Enabled Personalised, Curriculum-Grounded Feedback with Educators in the Loop

2025-07-06

AI Summary

This study addresses the inefficiency and time intensity of manually generating personalized, standards-aligned feedback by science teachers. We propose an educator-in-the-loop modular large language model system. Our approach features: (1) an error-aware assessment module that precisely identifies conceptual misconceptions in student responses; and (2) a curriculum-alignment generation mechanism based on topic-aware memory chains—replacing conventional retrieval—to significantly improve semantic consistency between feedback and curricular standards while suppressing noise. The system integrates structured curriculum knowledge, a lightweight error detection model, and an interactive supervision interface, enabling teachers to customize feedback policies and intervene in real time. Experiments demonstrate that our method reduces teacher feedback preparation time by 62% while preserving feedback quality and interpretability, and simultaneously increases student feedback adoption rates and learning outcomes—achieving scalability and pedagogical applicability.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

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.

Problem

• Generates personalized curriculum-aligned feedback in science education
• Captures nuanced reasoning errors for accurate assessment
• Reduces noise and improves relevance in feedback generation

Innovation

• LLM-based system for personalized science feedback
• Curriculum-grounded generation with topic-linked memory
• Educator-in-the-loop interface for customization