让大模型跨语言对齐文化知识，提升多语种公平性。
Cross-Lingual Consensus: Aligning Multilingual Cultural Knowledge via Multilingual Self-Consistency
- 用多语言自一致性筛选可靠文化回答，自动识别最优响应。
- 在BLEnD基准上，英语查询性能平均提升5.03%，仅依赖自生成数据。
- 适合关注AI文化偏见、多语种公平性的研究者与开发者。
尽管大语言模型在各类任务中表现出强大能力，但其在不同语言间存在显著性能差异。以英文提示时模型表现最佳，却常带来西方中心偏见，难以准确反映多元文化知识。我们假设，模型中已嵌入丰富的本地语言文化知识，但在英文提示下无法有效调用。为此，提出一种新型自监督框架：利用多语言自一致性识别跨语言中最可靠的响应，并结合自批判机制将知识迁移至弱语言。在BLEnD基准上的评估显示，该方法显著提升了文化对齐度——英语查询性能平均提升5.03%，且完全基于自生成数据。结果表明，潜在的文化知识可被成功挖掘并跨语言传播，实现更公平一致的大模型。
原文摘要 · Abstract (English)
Although Large Language Models (LLMs) demonstrate strong capabilities across various tasks, they exhibit significant performance discrepancies across languages. While prompting LLMs in English typically yields the highest general performance, it often induces a Western-centric bias, hindering the model's ability to accurately reflect diverse cultural knowledge. We hypothesize that LLMs already possess rich cultural knowledge embedded within local-language representations, but fail to retrieve it when prompted in English. To bridge this cross-lingual knowledge gap, we propose a novel self-supervised framework. Our method leverages multilingual self-consistency to identify the most reliable cultural responses across languages, combined with a self-critique mechanism to transfer this knowledge to the weaker language. Evaluations on the BLEnD benchmark demonstrate that our approach significantly improves cultural alignment-boosting performance on English queries by an average of 5.03%-relying entirely on self-generated data. Ultimately, our work demonstrates that latent cultural knowledge can be successfully surfaced and propagated across languages, enabling more culturally equitable and consistent 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。