--- title: "TOEBM at BEA 2026 Shared Task 1: Improving Lexical Difficulty" description: "The authors argue that training with only a scalar regression target leaves the embedding space… 2 references, cited by 1 paper here." authors: ["Wicaksono Leksono Muhamad", "Joanito Agili Lopo", "Tsamarah Rana Nugraha", "Ahmad Cahyono Adi", "Muhammad Oriza Nurfajri"] year: 2026 venue: "Proceedings of the 21st Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2026)" source: "https://aclanthology.org/2026.bea-1.81/" doi: "10.18653/v1/2026.bea-1.81" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/muhamad-2026-toebm-bea-2026-shared-task/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/muhamad-2026-toebm-bea-2026-shared-task/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/18/) / TOEBM at BEA 2026 Shared Task 1: Improving Lexical Difficulty Prediction with Context-Aligned Contrastive Learning and Ridge Ensembling # TOEBM at BEA 2026 Shared Task 1: Improving Lexical Difficulty Prediction with Context-Aligned Contrastive Learning and Ridge Ensembling **Authors:** [Wicaksono Leksono Muhamad](https://md.research.elamur.ai/free/en/authors/wicaksono-leksono-muhamad/), [Joanito Agili Lopo](https://md.research.elamur.ai/free/en/authors/joanito-agili-lopo/), Tsamarah Rana Nugraha, Ahmad Cahyono Adi and Muhammad Oriza Nurfajri · **Year:** 2026 · **Venue:** [Proceedings of the 21st Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2026)](https://md.research.elamur.ai/free/en/venues/bea/) ([BEA 2026](https://md.research.elamur.ai/free/en/venues/bea/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2026.bea-1.81/) · [PDF](https://aclanthology.org/2026.bea-1.81.pdf) · [DOI 10.18653/v1/2026.bea-1.81](https://doi.org/10.18653/v1/2026.bea-1.81) · [OpenAlex](https://openalex.org/W7166887640) **Citations:** 0 citations (OpenAlex, 2026-10-14) · [1](https://md.research.elamur.ai/free/en/papers/muhamad-2026-toebm-bea-2026-shared-task/cited-by/) in our library, of the 149,439 papers whose bibliographies we read ## Summary The paper tackles L1-aware lexical difficulty prediction for BEA 2026 Shared Task 1. The goal is to estimate how hard an English word is for learners with a particular first language. The authors argue that training with only a scalar regression target leaves the embedding space unstructured. In that setting, items of similar difficulty need not cluster, and cross-lingual alignment is not enforced. Their framework, Context-Aligned Contrastive Regression, adds two auxiliary objectives to MSE regression: - **Cross-View Context Contrastive loss:** pulls together encodings of the English target view and the full L1-aware input for the same item. - **Ordinal Soft Contrastive loss:** weights pairs by a Gaussian kernel over difficulty-score distance. Three multilingual encoders are trained independently with this objective, and their outputs are combined by a RidgeCV meta-regressor. The system is evaluated on Spanish, German and Chinese learner data. The ensemble beats each single encoder and keeps errors flatter across difficulty levels. It also corrects systematic under- and over-estimation by individual models. Representation analysis indicates better cross-lingual alignment and an ordinal structure in the embedding space. This matters for building level-appropriate learning materials and vocabulary assessments. ## Key points - **Data and labels:** three L1 groups (ES, DE, CN), with targets given as continuous GLMM difficulty scores. Lower GLMM scores mean harder words. - **Base encoders:** xlm-roberta-base, mdeberta-v3-base and mmBERT-base, stacked via ridge regression (RidgeCV). - **Error by difficulty bin:** XLM-R shows strong score compression, with error rising sharply on easier words. mmBERT shows moderate error growth, and mDeBERTa-v3 is the most stable single model. The Ridge ensemble has the lowest or near-lowest MAE in almost all bins. - **Qualitative example:** for ES "cruise" (GLMM 1.21), mmBERT predicts −0.50 while the ensemble predicts 1.23. - **Remaining failures:** some items stay far off even after ensembling, such as "baking", "stake" and "umbrella". The authors attribute these errors to ambiguity or context dependence. - **Code:** available at github.com/airlanggawicaksono/BEA2026TOEBM. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions - [University of Manchester](https://md.research.elamur.ai/free/en/universities/university-of-manchester/) — University, Manchester, United Kingdom · 87 works · 44,938 citations - [Universitas Gadjah Mada](https://md.research.elamur.ai/free/en/universities/universitas-gadjah-mada/) — University, Yogyakarta, Indonesia · 4 works · 56 citations 📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,552 works · [💭 Developmental and Educational Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/developmental-and-educational-psychology/) · 499 works ## Cite Cite as: Wicaksono Leksono Muhamad, Joanito Agili Lopo, Tsamarah Rana Nugraha, Ahmad Cahyono Adi and Muhammad Oriza Nurfajri. 2026. TOEBM at BEA 2026 Shared Task 1: Improving Lexical Difficulty Prediction with Context-Aligned Contrastive Learning and Ridge Ensembling. Proceedings of the 21st Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2026). The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{muhamad2026toebm, title = {{TOEBM at BEA 2026 Shared Task 1: Improving Lexical Difficulty Prediction with Context-Aligned Contrastive Learning and Ridge Ensembling}}, author = {Wicaksono Leksono Muhamad, Joanito Agili Lopo, Tsamarah Rana Nugraha, Ahmad Cahyono Adi and Muhammad Oriza Nurfajri}, booktitle = {Proceedings of the 21st Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2026)}, year = {2026}, doi = {10.18653/v1/2026.bea-1.81}, url = {https://doi.org/10.18653/v1/2026.bea-1.81} } ``` - [← previous TinyAttack: Exploring Stylistic Vulnerabilities in Large Language Models](https://md.research.elamur.ai/free/en/papers/mamta-2026-tinyattack-exploring-stylistic-vulnerabilities-large/) - [next → Token Titans at BEA 2026 Shared Task 1: Multilingual Lexical Complexity Prediction via Fine-Tuned XLM-RoBERTa with Ensemble Decoding](https://md.research.elamur.ai/free/en/papers/parashar-2026-token-titans-bea-2026-shared/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/18/) ## References 2 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. The authors gratefully acknowledge Mantera Studio for providing the computational resources and APIs utilized in this research. Additionally, this work was partially supported by the 2026 Publication Funding from the Department of Computer Science and Electronics at Universitas Gadjah Mada. [find](https://scholar.google.com/scholar?q=The+authors+gratefully+acknowledge+Mantera+Studio+for+providing+the+computational+resources+and+APIs+utilized+in+this+research%2E+Additionally%2C+this+work+was+partially+supported+by+the+2026+Publication+) 2. Hasan Alisoy. 2024. Exploring language acquisition: The role of native language interference in esl learners. Journal of Azerbaijan Language and Education Studies, 1(1):50–66. \#\# Limitations [find](https://scholar.google.com/scholar?q=Hasan+Alisoy%2E+2024%2E+Exploring+language+acquisition%3A+The+role+of+native+language+interference+in+esl+learners%2E+Journal+of+Azerbaijan+Language+and+Education+Studies%2C+1%281%29%3A50%E2%80%9366%2E+%5C%23%5C%23+Limitations) *Updated 31 October 2026*