Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2605.14257 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911704123703296 |
|---|---|
| author | Nohejl, Adam Wu, Xuanxin Ide, Yusuke Machin, Maria Angelica Riera Chang, Yi-Ning Yanaka, Hitomi |
| author_facet | Nohejl, Adam Wu, Xuanxin Ide, Yusuke Machin, Maria Angelica Riera Chang, Yi-Ning Yanaka, Hitomi |
| contents | 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/ynklab/vocabulary-difficulty . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_14257 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Sakura at BEA 2026 Shared Task 1: What Makes Vocabulary Difficult? Nohejl, Adam Wu, Xuanxin Ide, Yusuke Machin, Maria Angelica Riera Chang, Yi-Ning Yanaka, Hitomi Computation and Language 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/ynklab/vocabulary-difficulty . |
| title | Sakura at BEA 2026 Shared Task 1: What Makes Vocabulary Difficult? |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2605.14257 |