What Makes Words Hard? Sakura at BEA 2026 Shared Task on Vocabulary Difficulty Prediction
This work provides top-performing models and insights for vocabulary difficulty prediction, benefiting educators and test designers, though the approach is incremental.
The authors developed a high-accuracy black-box model (r > 0.91) and an explainable model (r > 0.77) for vocabulary difficulty prediction, with the black-box model achieving the top result in the shared task. They found that item difficulty in the KVL dataset is influenced by spelling difficulty and test item construction beyond genuine word difficulty.
We describe two types of models for vocabulary difficulty prediction: a high-accuracy black-box model, which achieved the top shared task result in the open track, and an explainable model, which outperforms a fine-tuned encoder baseline. As the black-box model, we fine-tuned an LLM using a soft-target loss function for effective application to the rating task, achieving r > 0.91. The explainable model provides insights into what impacts the difficulty of each item while maintaining a strong correlation (r > 0.77). We further analyze the results, demonstrating that the difficulty of items in the British Council's Knowledge-based Vocabulary Lists (KVL) is often affected by spelling difficulty or the construction of the test items, in addition to the genuine production difficulty of the words. We make our code available online at https://github.com/adno/vocabulary-difficulty .