揭示大模型跨语言学新知识时的不平等现象
Uncovering inequalities in new knowledge learning by large language models across different languages
- 从效果、迁移、优先级、鲁棒性四维度分析跨语言学习差异
- 低资源语言在所有维度均显著落后于高资源语言
- 适用于关注AI公平性与多语言模型优化的研究者
随着大语言模型（LLMs）逐渐成为全球日常问题解决的重要工具，理解语言不平等问题变得日益关键。现有研究主要聚焦于静态分析，评估不同语言下模型已有知识与能力的差异。然而，LLMs持续演进，不断获取新知识以生成最新、领域特定的回答。因此，研究这一动态过程中的语言不平等也至关重要。本文探讨了大模型在跨语言新知识学习中的不平等现象，涵盖有效性、可迁移性、优先级和鲁棒性四个关键维度。通过在上下文学习和微调两种设置下，使用专有及开源模型进行大量实验，我们发现低资源语言在所有维度均持续处于劣势。本研究旨在揭示这些差异，提升对大模型新知识学习中语言不平等的认知，推动更包容、更公平的未来大模型发展。
原文摘要 · Abstract (English)
As large language models (LLMs) gradually become integral tools for problem solving in daily life worldwide, understanding linguistic inequality is becoming increasingly important. Existing research has primarily focused on static analyses that assess the disparities in the existing knowledge and capabilities of LLMs across languages. However, LLMs are continuously evolving, acquiring new knowledge to generate up-to-date, domain-specific responses. Investigating linguistic inequalities within this dynamic process is, therefore, also essential. In this paper, we explore inequalities in new knowledge learning by LLMs across different languages and four key dimensions: effectiveness, transferability, prioritization, and robustness. Through extensive experiments under two settings (in-context learning and fine-tuning) using both proprietary and open-source models, we demonstrate that low-resource languages consistently face disadvantages across all four dimensions. By shedding light on these disparities, we aim to raise awareness of linguistic inequalities in LLMs' new knowledge learning, fostering the development of more inclusive and equitable future LLMs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。