WordCraft: Scaffolding the Keyword Method for L2 Vocabulary Learning with Multimodal LLMs
On the map: Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning
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.
Key facts. No citing papers in the map yet (data through 7 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.
Builds on
21 of 124 references.
References · 21
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2021A Survey of Human-in-the-loop for Machine Learningcited by 214
- 2023Hallucinations in Large Multilingual Translation Modelscited by 126
- 2023Storyfier: Exploring Vocabulary Learning Support with Text Generation Modelscited by 12
- 2024Investigating Interaction Modes and User Agency in Human-LLM Collaboration for Domain-Specific Data Analysiscited by 12
- 2016Unbounded Human Learning: Optimal Scheduling for Spaced Repetitioncited by 11
- 2024HILL: A Hallucination Identifier for Large Language Modelscited by 11
- 2024TypeDance: Creating Semantic Typographic Logos from Image through Personalized Generationcited by 10
- 2024Exploring How Multiple Levels of GPT-Generated Programming Hints Support or Disappoint Novicescited by 10
- 2024Amuse: Human-AI Collaborative Songwriting with Multimodal Inspirationscited by 9
- 2025DBox: Scaffolding Algorithmic Programming Learning through Learner-LLM Co-Decompositioncited by 9
- 2025Brickify: Enabling Expressive Design Intent Specification through Direct Manipulation on Design Tokenscited by 8
9 more
- 2025SketchFlex: Facilitating Spatial-Semantic Coherence in Text-to-Image Generation with Region-Based Sketchescited by 6
- 2024PAIGE: Examining Learning Outcomes and Experiences with Personalized AI-Generated Educational Podcastscited by 5
- 2024Exploring Automated Keyword Mnemonics Generation with Large Language Models via Overgenerate-and-Rankcited by 4
- 2025ClueCart: Supporting Game Story Interpretation and Narrative Inference from Fragmented Cluescited by 3
- 2022VocabulARy: Learning Vocabulary in AR Supported by Keyword Visualisationscited by 2
- 2024RetAssist: Facilitating Vocabulary Learners with Generative Images in Story Retelling Practicescited by 1
- 2025Text-to-Image Generation for Vocabulary Learning Using the Keyword Methodcited by 1
- 2025Advancing Problem-Based Learning with Clinical Reasoning for Improved Differential Diagnosis in Medical Educationcited by 1
- 2025PhoniTale: Phonologically Grounded Mnemonic Generation for Typologically Distant Language Pairscited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025P-CoT: A Pedagogically-motivated Participatory Chain-of-Thought Prompting for Phonological Reasoning in LLMs
- 2025MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks
- 2025Shared Path: Unraveling Memorization in Multilingual LLMs through Language Similarities
- 2024The Prompt Canvas: A Literature-Based Practitioner Guide for Creating Effective Prompts in Large Language Models
- 2024Benchmarking Cognitive Domains for LLMs: Insights from Taiwanese Hakka Culture
- 2025Simplifications are Absolutists: How Simplified Language Reduces Word Sense Awareness in LLM-Generated Definitions
- 2023FollowEval: A Multi-Dimensional Benchmark for Assessing the Instruction-Following Capability of Large Language Models
- 2024MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMs