English

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

Computers and Society 2025-10-15 v4 Artificial Intelligence Computation and Language Human-Computer Interaction

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.

Keywords

Cite

@article{arxiv.2507.04295,
  title  = {LearnLens: LLM-Enabled Personalised, Curriculum-Grounded Feedback with Educators in the Loop},
  author = {Runcong Zhao and Artem Bobrov and Jiazheng Li and Cesare Aloisi and Yulan He},
  journal= {arXiv preprint arXiv:2507.04295},
  year   = {2025}
}

Comments

EMNLP 2025

R2 v1 2026-07-01T03:48:10.208Z