Towards ordinal few-shot learning for automated essay grading.

Wijayasekara, Vihanga Ashinsana; Martin, Kyle; Wiratunga, Nirmalie

Abstract

Ordinal essay grading, an essential task in educational domain and natural language processing (NLP), involves categorising essays based on quality, such as grading scale levels. This is crucial in automated assessment systems that evaluate student writing and provide feedback on aspects like coherence, argumentation, and language proficiency. However, challenges arise from limited data resources, such as when a new assessment is introduced and no data is available to train algorithms, as well as the complexity of essay structures in real-world grading scenarios. This research explores the use of few-shot learning, a technique that learns from a limited number of labeled examples, to address these challenges in ordinal essay grading. By leveraging few-shot learning's ability to identify class representations from minimal examples, we aim to mitigate data scarcity in essay grading. With the rise of Large Language Models (LLMs), we seek to improve few-shot prompting performance by introducing novel strategies for example selection, enhancing class representation in the demonstrations provided to prompts. Finally, we aim to apply prototypical methods to agents architectures for agent selection on the basis of similarity weighted by ordinal class knowledge.

Citation

WIJAYASEKARA, V.A., MARTIN, K. and WIRATUNGA, N. 2025. Towards ordinal few-shot learning for automated essay grading. In Cristea, A.I., Walker, E., Lu, Y., Santos, O.C. and Isotani, S. (eds.) Artificial intelligence in education. Posters and late breaking results, workshops and tutorials, industry and innovation tracks, practitioners, doctoral consortium, Blue Sky, and WideAIED: proceedings of the 26th International conference in Artificial intelligence in education 2025 (AIED 2025), 22-26 July 2026, Palermo, Italy. Communications in computer and information science, 2590. Cham: Springer [online], part 1, pages 346-351. Available from: https://doi.org/10.1007/978-3-031-99261-2_35

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 26th International conference in Artificial intelligence in education 2025 (AIED 2025)
• Start Date: Jul 22, 2025
• End Date: Jul 26, 2025
• Acceptance Date: Mar 20, 2025
• Online Publication Date: Jul 21, 2025
• Publication Date: Dec 31, 2025
• Deposit Date: Aug 15, 2025
• Publicly Available Date: Jul 22, 2026
• Publisher: Springer
• Peer Reviewed: Peer Reviewed
• Pages: 346-351
• Series Title: Communications in computer and information science (CCIS)
• Series Number: 2590
• Series ISSN: 1865-0929; 1865-0937
• Book Title: Artificial intelligence in education: posters and late breaking results, workshops and tutorials, industry and innovation tracks, practitioners, doctoral consortium, Blue Sky, and WideAIED
• ISBN: 9783031992605
• DOI: https://doi.org/10.1007/978-3-031-99261-2_35
• Keywords: Essay grading; Few-shot learning; Few-shot prompting
• Public URL: https://rgu-repository.worktribe.com/output/2973989