# Prompt Balance Matters: Understanding How Imbalanced Few-Shot Learning Affects Multilingual Sense Disambiguation in LLMs

arXiv: https://arxiv.org/abs/2510.03762 · HTML: https://mlsanity.com/paper/2510.03762/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 28 references that are in the map.
- First posted on arXiv 4 Oct 2025.

## Builds on (most cited first, 9 of 9)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach](https://mlsanity.com/paper/2010.07835/) (2020)
- [All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages](https://mlsanity.com/paper/2411.16508/) (2024)
- [The Language Model Understood the Prompt was Ambiguous: Probing Syntactic Uncertainty Through Generation](https://mlsanity.com/paper/2109.07848/) (2021)
- [What do Language Models know about word senses? Zero-Shot WSD with Language Models and Domain Inventories](https://mlsanity.com/paper/2302.03353/) (2023)
- [Active Few-Shot Learning for Text Classification](https://mlsanity.com/paper/2502.18782/) (2025)
- [Thank You, Stingray: Multilingual Large Language Models Can Not (Yet) Disambiguate Cross-Lingual Word Sense](https://mlsanity.com/paper/2410.21573/) (2024)
- [Balancing Label Quantity and Quality for Scalable Elicitation](https://mlsanity.com/paper/2410.13215/) (2024)

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

- [DACE For Railway Acronym Disambiguation](https://mlsanity.com/paper/2512.18357/) (2025)

## Abstract (arXiv)

Recent advances in Large Language Models (LLMs) have significantly reshaped the landscape of Natural Language Processing (NLP). Among the various prompting techniques, few-shot prompting has gained considerable attention for its practicality and effectiveness. This study investigates how few-shot prompting strategies impact the Word Sense Disambiguation (WSD) task, particularly focusing on the biases introduced by imbalanced sample distributions. We use the GLOSSGPT prompting method, an advanced approach for English WSD, to test its effectiveness across five languages: English, German, Spanish, French, and Italian. Our results show that imbalanced few-shot examples can cause incorrect sense predictions in multilingual languages, but this issue does not appear in English. To assess model behavior, we evaluate both the GPT-4o and LLaMA-3.1-70B models and the results highlight the sensitivity of multilingual WSD to sample distribution in few-shot settings, emphasizing the need for balanced and representative prompting strategies.