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

arXiv: https://arxiv.org/abs/2602.00762 · HTML: https://mlsanity.com/paper/2602.00762/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 21 of its 124 references that are in the map.
- First posted on arXiv 31 Jan 2026.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 21 of 21)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [A Survey of Human-in-the-loop for Machine Learning](https://mlsanity.com/paper/2108.00941/) (2021)
- [Hallucinations in Large Multilingual Translation Models](https://mlsanity.com/paper/2303.16104/) (2023)
- [Unbounded Human Learning: Optimal Scheduling for Spaced Repetition](https://mlsanity.com/paper/1602.07032/) (2016)
- [Storyfier: Exploring Vocabulary Learning Support with Text Generation Models](https://mlsanity.com/paper/2308.03864/) (2023)
- [Investigating Interaction Modes and User Agency in Human-LLM Collaboration for Domain-Specific Data Analysis](https://mlsanity.com/paper/2405.05548/) (2024)
- [HILL: A Hallucination Identifier for Large Language Models](https://mlsanity.com/paper/2403.06710/) (2024)
- [TypeDance: Creating Semantic Typographic Logos from Image through Personalized Generation](https://mlsanity.com/paper/2401.11094/) (2024)
- [Exploring How Multiple Levels of GPT-Generated Programming Hints Support or Disappoint Novices](https://mlsanity.com/paper/2404.02213/) (2024)
- [Amuse: Human-AI Collaborative Songwriting with Multimodal Inspirations](https://mlsanity.com/paper/2412.18940/) (2024)
- [DBox: Scaffolding Algorithmic Programming Learning through Learner-LLM Co-Decomposition](https://mlsanity.com/paper/2502.19133/) (2025)
- [Brickify: Enabling Expressive Design Intent Specification through Direct Manipulation on Design Tokens](https://mlsanity.com/paper/2502.21219/) (2025)
- [SketchFlex: Facilitating Spatial-Semantic Coherence in Text-to-Image Generation with Region-Based Sketches](https://mlsanity.com/paper/2502.07556/) (2025)
- [PAIGE: Examining Learning Outcomes and Experiences with Personalized AI-Generated Educational Podcasts](https://mlsanity.com/paper/2409.04645/) (2024)
- [Exploring Automated Keyword Mnemonics Generation with Large Language Models via Overgenerate-and-Rank](https://mlsanity.com/paper/2409.13952/) (2024)
- [ClueCart: Supporting Game Story Interpretation and Narrative Inference from Fragmented Clues](https://mlsanity.com/paper/2503.06098/) (2025)
- [VocabulARy: Learning Vocabulary in AR Supported by Keyword Visualisations](https://mlsanity.com/paper/2207.00896/) (2022)
- [RetAssist: Facilitating Vocabulary Learners with Generative Images in Story Retelling Practices](https://mlsanity.com/paper/2405.14794/) (2024)
- [Text-to-Image Generation for Vocabulary Learning Using the Keyword Method](https://mlsanity.com/paper/2501.17099/) (2025)
- [Advancing Problem-Based Learning with Clinical Reasoning for Improved Differential Diagnosis in Medical Education](https://mlsanity.com/paper/2503.06099/) (2025)
- [PhoniTale: Phonologically Grounded Mnemonic Generation for Typologically Distant Language Pairs](https://mlsanity.com/paper/2507.05444/) (2025)

## Abstract (arXiv)

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.