King's College London NLP

AI for Education

Using LLMs for explainable student answer assessment and personalised feedback for secondary school science education.

Participants

Jiazheng Li, Runcong Zhao, Artem Bobrov, Yuxiang Zhou, Lin Gui, Yulan He

Projects

AI-enabled High-Stakes Assessment, (2025-2028), funded by EPSRC.
Personalised AI feedback for secondary school science (Dec 2024 – Apr 2025), funded by the Department for Education, UK.
Automated Scoring System for GCSE Science Exams, (2022-2026), funded by AQA.
Elandi: trustworthy generative AI for affordable personalised learning and development (2024-2025), funded by Innovate UK under the Accelerating Trustworthy AI: Phase 2 Collaborative R&D call, led by AI for Global Goals.

Publications

J. Li, Y. Zhou, J. Lu, G. Tyen, L. Gui, C. Aloisi and Y. He. Two Heads Are Better Than One: Dual-Model Verbal Reflection at Inference-Time , arXiv:2502.19230, 2025.
J. Li, A. Bobrov, D. West, C. Aloisi and Y. He. An Automated Explainable Educational Assessment System Built on LLMs , The 39th Annual AAAI Conference on Artificial Intelligence (AAAI), 2025.
J. Li, A. Bobrov, D. West, C. Aloisi and Y. He. AERA Chat: An Interactive Platform for Automated Explainable Student Answer Assessment , arXiv:2410.09507, 2024.
J. Li, H. Xu, Z. Sun, Y. Zhou, D. West, C. Aloisi and Y. He. Calibrating LLMs with Preference Optimization on Thought Trees for Generating Rationales in Science Question Scoring , Findings of EMNLP, 2024.
J. Li, L. Gui, Y. Zhou, D. West, C. Aloisi and Y. He. Exploring Explainable Automated Student Answer Assessment with ChatGPT , Findings of EMNLP, 2023.