# SwanNLP at SemEval-2026 Task 5: An LLM-based Framework for Plausibility Scoring in Narrative Word Sense Disambiguation

arXiv: https://arxiv.org/abs/2604.16262 · HTML: https://mlsanity.com/paper/2604.16262/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 22 references that are in the map.
- First posted on arXiv 17 Apr 2026.

## Builds on (most cited first, 8 of 8)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [FEWS: Large-Scale, Low-Shot Word Sense Disambiguation with the Dictionary](https://mlsanity.com/paper/2102.07983/) (2021)
- [Exploring the Word Sense Disambiguation Capabilities of Large Language Models](https://mlsanity.com/paper/2503.08662/) (2025)
- [Do Large Language Models Understand Word Senses?](https://mlsanity.com/paper/2509.13905/) (2025)
- [What do Language Models know about word senses? Zero-Shot WSD with Language Models and Domain Inventories](https://mlsanity.com/paper/2302.03353/) (2023)
- [Thank You, Stingray: Multilingual Large Language Models Can Not (Yet) Disambiguate Cross-Lingual Word Sense](https://mlsanity.com/paper/2410.21573/) (2024)
- [An Exploration-Analysis-Disambiguation Reasoning Framework for Word Sense Disambiguation with Low-Parameter LLMs](https://mlsanity.com/paper/2603.05400/) (2026)

## Abstract (arXiv)

Recent advances in language models have substantially improved Natural Language Understanding (NLU). Although widely used benchmarks suggest that Large Language Models (LLMs) can effectively disambiguate, their practical applicability in real-world narrative contexts remains underexplored. SemEval-2026 Task 5 addresses this gap by introducing a task that predicts the human-perceived plausibility of a word sense within a short story. In this work, we propose an LLM-based framework for plausibility scoring of homonymous word senses in narrative texts using a structured reasoning mechanism. We examine the impact of fine-tuning low-parameter LLMs with diverse reasoning strategies, alongside dynamic few-shot prompting for large-parameter models, on accurate sense identification and plausibility estimation. Our results show that commercial large-parameter LLMs with dynamic few-shot prompting closely replicate human-like plausibility judgments. Furthermore, model ensembling slightly improves performance, better simulating the agreement patterns of five human annotators compared to single-model predictions