MAPLE: A Meta-learning Framework for Cross-Prompt Essay Scoring

2026-04-19

AI Summary

This work addresses the limited generalization of automatic essay scoring (AES) systems in cross-prompt settings by proposing MAPLE, a novel framework that introduces prototypical networks to cross-prompt AES for the first time. Integrating meta-learning, MAPLE learns transferable essay representations from multi-prompt data, enabling a unified and robust scoring system capable of handling multilingual inputs and heterogeneous scoring rubrics. Experimental results demonstrate that MAPLE achieves state-of-the-art performance in cross-prompt AES, outperforming strong baselines by 8.5 and 3.0 points in Quadratic Weighted Kappa (QWK) on the ELLIPSE and LAILA datasets, respectively, and yielding significant improvements across multiple scoring traits in the ASAP benchmark.

Technology Category

• Natural Language Processing: Prompt Engineering / Prompting
• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Multiagent Learning

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Automated Essay Scoring (AES) faces significant challenges in cross-prompt settings, where models must generalize to unseen writing prompts. To address this limitation, we propose MAPLE, a meta-learning framework that leverages prototypical networks to learn transferable representations across different writing prompts. Across three diverse datasets (ELLIPSE and ASAP (English), and LAILA (Arabic)), MAPLE achieves state-of-the-art performance on ELLIPSE and LAILA, outperforming strong baselines by 8.5 and 3 points in QWK, respectively. On ASAP, where prompts exhibit heterogeneous score ranges, MAPLE yields improvements on several traits, highlighting the strengths of our approach in unified scoring settings. Overall, our results demonstrate the potential of meta-learning for building robust cross-prompt AES systems.

Problem

• Automated Essay Scoring
• cross-prompt
• generalization
• unseen prompts
• meta-learning

Innovation

• meta-learning
• prototypical networks
• cross-prompt essay scoring
• automated essay scoring
• transferable representations