WordCraft: Scaffolding the Keyword Method for L2 Vocabulary Learning with Multimodal LLMs
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911413253963776 |
|---|---|
| author | Shao, Yuheng Xiong, Junjie Wu, Chaoran Wang, Xiyuan Zhou, Ziyu Ouyang, Yang Tao, Qinyi Li, Quan |
| author_facet | Shao, Yuheng Xiong, Junjie Wu, Chaoran Wang, Xiyuan Zhou, Ziyu Ouyang, Yang Tao, Qinyi Li, Quan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_00762 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | WordCraft: Scaffolding the Keyword Method for L2 Vocabulary Learning with Multimodal LLMs Shao, Yuheng Xiong, Junjie Wu, Chaoran Wang, Xiyuan Zhou, Ziyu Ouyang, Yang Tao, Qinyi Li, Quan Computation and Language Human-Computer Interaction 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. |
| title | WordCraft: Scaffolding the Keyword Method for L2 Vocabulary Learning with Multimodal LLMs |
| topic | Computation and Language Human-Computer Interaction |
| url | https://arxiv.org/abs/2602.00762 |