WordCraft: Scaffolding the Keyword Method for L2 Vocabulary Learning with Multimodal LLMs

2026-01-31

AI Summary

This study addresses the challenges faced by L1 Chinese–L2 English learners in effectively applying the keyword method for vocabulary retention, particularly difficulties in generating phonologically matched keywords, constructing coherent semantic associations, and forming vivid mental imagery—factors that undermine long-term memory. To mitigate these issues, the authors design and implement WordCraft, a learner-centered interactive tool that leverages multimodal large language models (MLLMs) to deliver process-oriented, scaffolded instruction. WordCraft guides users step-by-step through keyword selection, semantic linking, and visual imagery generation, thereby preserving the generation effect while offering structured cognitive support. Two user studies demonstrate that WordCraft significantly outperforms baseline approaches in vocabulary retention, system usability, and learner engagement.

Technology Category

• Natural Language Processing: Lexical Semantics and Morphology
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Applying the keyword method for vocabulary memorization remains a significant challenge for L1 Chinese-L2 English learners. They frequently struggle to generate phonologically appropriate keywords, construct coherent associations, and create vivid mental imagery to aid long-term retention. Existing approaches, including fully automated keyword generation and outcome-oriented mnemonic aids, either compromise learner engagement or lack adequate process-oriented guidance. To address these limitations, we conducted a formative study with L1 Chinese-L2 English learners and educators (N=18), which revealed key difficulties and requirements in applying the keyword method to vocabulary learning. Building on these insights, we introduce WordCraft, a learner-centered interactive tool powered by Multimodal Large Language Models (MLLMs). WordCraft scaffolds the keyword method by guiding learners through keyword selection, association construction, and image formation, thereby enhancing the effectiveness of vocabulary memorization. Two user studies demonstrate that WordCraft not only preserves the generation effect but also achieves high levels of effectiveness and usability.

Problem

• keyword method
• L2 vocabulary learning
• mental imagery
• phonological association
• vocabulary memorization

Innovation

• Multimodal LLMs
• keyword method
• scaffolding
• L2 vocabulary learning
• interactive tool