This system for SemEval-2026 Task 5 is reported, which predicts graded plausibility scores for target word senses in narrative context and shows that distribution modeling better aligns with human plausibility judgments than single-score prediction.
Abstract
Here, we report our system for SemEval-2026 Task 5 (Gehring et al., 2026), which predicts graded plausibility scores for target word senses in narrative context. We explore embedding-based similarity, transformer fine-tuning, and a three-stage curriculum combining WiC pretraining, Wasserstein distribution learning, and KL-based calibration. Our best model, DeBERTa-xLarge with curriculum training, achieves 78% accuracy within one standard deviation and a Spearman Correlation of 0.70 , with an overall test score of 0.74. Results show that distribution modeling better aligns with human plausibility judgments than single-score prediction.
A system that associates a fixed list of 50 words with each WordNet synset, and computes several scores for each of the phrases in the story, to determine how closely the phrase matches the wordlist is inappropriate for this dataset.
This paper utilized a pre-trained DeBERTa-V3 backbone to capture semantic meaning through disentangled attention to capture semantic meaning through disentangled attention, and proposed a Hybrid MSE-CCC Loss to identify distributional relationships that simple regression missed.
This paper presents the implementation approach used in the First Chinese Factivity Inference Evaluation 2025 (FIE2025), which aims to enhance LLM’s discriminative capability by adequately integrating the task-specific information via prompts, as well as constructing dynamic few-shot datasets for fine-tuning.
This study explores the semantic competence of Italian BabyLMs, focusing on their sensitivity to semantic violations, using a minimal pair benchmark targeting semantic violations to evaluate the semantic abilities of BAMBI, a family of small-scale models trained on progressively larger and more complex datasets.
A. Suozzi, Luca Capone, Gianluca Lebani et al.· 0 citations
The results show that encoder-based metrics remain highly competitive, while generative LLMs perform strongly in hypothesis comparison and improve the interpretability of ASR evaluation.
Thibault Bañeras-Roux, Shashi Kumar, Driss Khalil et al.· 0 citations
This work studies the task of ranking case-law sentences by their usefulness for explaining a concept or target statutory term, using an established dataset of 26,959 sentences covering 42 U.S. Code concepts labeled into four explanatory-value categories.
