提示平衡至关重要：理解不平衡少样本学习如何影响大语言模型中的多语言词义消歧
Prompt Balance Matters: Understanding How Imbalanced Few-Shot Learning Affects Multilingual Sense Disambiguation in LLMs
AI总结：
本研究针对少样本提示中样本分布不平衡的问题，采用GLOSSGPT提示法在五种语言上测试，发现不平衡样本会引发多语言词义消歧偏差，强调需采用平衡的提示策略。
摘要：
大语言模型（LLM）的最新进展显著重塑了自然语言处理（NLP）的格局。在各类提示技术中，少样本提示凭借其实用性和有效性受到广泛关注。本研究探究少样本提示策略如何影响词义消歧（WSD）任务，重点关注不平衡样本分布带来的偏差。我们采用GLOSSGPT提示法——一种面向英语WSD的先进方法——测试其在英语、德语、西班牙语、法语和意大利语五种语言中的效果。结果表明，不平衡的少样本示例会在多语言场景中导致错误的词义预测，但该问题在英语中并未出现。为评估模型行为，我们同时测试了GPT-4o和LLaMA-3.1-70B模型，结果凸显了少样本设置下多语言WSD对样本分布的敏感性，强调了采用平衡且具代表性的提示策略的必要性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
