# An Exploration-Analysis-Disambiguation Reasoning Framework for Word Sense Disambiguation with Low-Parameter LLMs

arXiv: https://arxiv.org/abs/2603.05400 · HTML: https://mlsanity.com/paper/2603.05400/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 19 of its 69 references that are in the map.
- First posted on arXiv 5 Mar 2026.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 19 of 19)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Qwen2.5-1M Technical Report](https://mlsanity.com/paper/2501.15383/) (2025)
- [Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision](https://mlsanity.com/paper/2109.08203/) (2021)
- [GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledge](https://mlsanity.com/paper/1908.07245/) (2019)
- [SenseBERT: Driving Some Sense into BERT](https://mlsanity.com/paper/1908.05646/) (2019)
- [Beyond Efficiency: A Systematic Survey of Resource-Efficient Large Language Models](https://mlsanity.com/paper/2401.00625/) (2024)
- [Exploring the Impact of Temperature on Large Language Models:Hot or Cold?](https://mlsanity.com/paper/2506.07295/) (2025)
- [Incorporating Glosses into Neural Word Sense Disambiguation](https://mlsanity.com/paper/1805.08028/) (2018)
- [Linguistic ambiguity analysis in ChatGPT](https://mlsanity.com/paper/2302.06426/) (2023)
- [Exploring the Word Sense Disambiguation Capabilities of Large Language Models](https://mlsanity.com/paper/2503.08662/) (2025)
- [Connect-the-Dots: Bridging Semantics between Words and Definitions via Aligning Word Sense Inventories](https://mlsanity.com/paper/2110.14091/) (2021)
- [Multiple Sources are Better Than One: Incorporating External Knowledge in Low-Resource Glossing](https://mlsanity.com/paper/2406.11085/) (2024)
- [Thank You, Stingray: Multilingual Large Language Models Can Not (Yet) Disambiguate Cross-Lingual Word Sense](https://mlsanity.com/paper/2410.21573/) (2024)
- [SenWiCh: Sense-Annotation of Low-Resource Languages for WiC using Hybrid Methods](https://mlsanity.com/paper/2505.23714/) (2025)
- [Translate to Disambiguate: Zero-shot Multilingual Word Sense Disambiguation with Pretrained Language Models](https://mlsanity.com/paper/2304.13803/) (2023)
- [SANDWiCH: Semantical Analysis of Neighbours for Disambiguating Words in Context ad Hoc](https://mlsanity.com/paper/2503.05958/) (2025)

## Built on by (most cited first, 1 of 1)

- [SwanNLP at SemEval-2026 Task 5: An LLM-based Framework for Plausibility Scoring in Narrative Word Sense Disambiguation](https://mlsanity.com/paper/2604.16262/) (2026)

## Abstract (arXiv)

Word Sense Disambiguation (WSD) remains a key challenge in Natural Language Processing (NLP), especially when dealing with rare or domain-specific senses that are often misinterpreted. While modern high-parameter Large Language Models (LLMs) such as GPT-4-Turbo have shown state-of-the-art WSD performance, their computational and energy demands limit scalability. This study investigates whether low-parameter LLMs (<4B parameters) can achieve comparable results through fine-tuning strategies that emphasize reasoning-driven sense identification. Using the FEWS dataset augmented with semi-automated, rationale-rich annotations, we fine-tune eight small-scale open-source LLMs (e.g. Gemma and Qwen). Our results reveal that Chain-of-Thought (CoT)-based reasoning combined with neighbour-word analysis achieves performance comparable to GPT-4-Turbo in zero-shot settings. Importantly, Gemma-3-4B and Qwen-3-4B models consistently outperform all medium-parameter baselines and state-of-the-art models on FEWS, with robust generalization to unseen senses. Furthermore, evaluation on the unseen "Fool Me If You Can'' dataset confirms strong cross-domain adaptability without task-specific fine-tuning. This work demonstrates that with carefully crafted reasoning-centric fine-tuning, low-parameter LLMs can deliver accurate WSD while substantially reducing computational and energy demands.