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

TL;DR

WordCraft is an interactive tool leveraging multimodal large language models to scaffold the keyword method, helping Chinese-L2 English learners improve vocabulary memorization through guided association and imagery creation.

Contribution

This paper introduces WordCraft, a novel multimodal LLM-powered tool that provides process-oriented guidance for the keyword method in L2 vocabulary learning.

Findings

WordCraft enhances vocabulary retention compared to baseline methods.

Learners report high usability and engagement with WordCraft.

The tool preserves the generation effect in vocabulary memorization.

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.