Conference Paper/Proceeding/Abstract 228 views 119 downloads
Prompt Balance Matters: Understanding How Imbalanced Few-Shot Learning Affects Multilingual Sense Disambiguation in LLMs
,
Nicholas Micallef ,
Julian Hough
Proceedings of the Workshop on Beyond English: Natural Language Processing for all Languages in an Era of Large Language Models, Pages: 7 - 15
Swansea University Authors:
Deshan Sumanathilaka , Nicholas Micallef , Julian Hough
-
PDF | Accepted Manuscript
Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention).
Download (461.14KB)
Abstract
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 pr...
| Published in: | Proceedings of the Workshop on Beyond English: Natural Language Processing for all Languages in an Era of Large Language Models |
|---|---|
| ISBN: | 978-954-452-105-9 |
| Published: |
Shoumen, Bulgaria
INCOMA Ltd.
2025
|
| Online Access: |
https://acl-bg.org/proceedings/2025/GlobalNLP%202025/index.html |
| URI: | https://cronfa.swan.ac.uk/Record/cronfa70198 |
| Abstract: |
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. |
|---|---|
| College: |
Faculty of Science and Engineering |
| Funders: |
Hough’s work is supported by the EPSRC grant EP/X009343/1 ‘FLUIDITY’. |
| Start Page: |
7 |
| End Page: |
15 |