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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Sumanathilaka, Deshan, Micallef, Nicholas, Hough, Julian
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911191837704192
author Sumanathilaka, Deshan
Micallef, Nicholas
Hough, Julian
author_facet Sumanathilaka, Deshan
Micallef, Nicholas
Hough, Julian
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_03762
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Prompt Balance Matters: Understanding How Imbalanced Few-Shot Learning Affects Multilingual Sense Disambiguation in LLMs
Sumanathilaka, Deshan
Micallef, Nicholas
Hough, Julian
Computation and Language
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.
title Prompt Balance Matters: Understanding How Imbalanced Few-Shot Learning Affects Multilingual Sense Disambiguation in LLMs
topic Computation and Language
url https://arxiv.org/abs/2510.03762