Commercial large LLMs using dynamic few-shot prompting and ensembling closely match human plausibility judgments on word senses in narratives, outperforming single models and fine-tuned smaller models.
Scoring Rubric: • 5: Perfectly plausible.The meaning is strongly supported by the entire context, and all parts of the story form a consistent, logical narrative
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SwanNLP at SemEval-2026 Task 5: An LLM-based Framework for Plausibility Scoring in Narrative Word Sense Disambiguation
Commercial large LLMs using dynamic few-shot prompting and ensembling closely match human plausibility judgments on word senses in narratives, outperforming single models and fine-tuned smaller models.