让大模型尊重文化差异，避免千篇一律的平均值。
CuMA: Aligning LLMs with Sparse Cultural Values via Demographic-Aware Mixture of Adapters
- 用带人口属性的专家混合框架，分离不同文化价值观的梯度。
- 在多个数据集上超越现有方法，显著减少文化均值坍缩。
- 适合关注多文化场景下模型公平性的研究者使用。
大型语言模型面向全球用户时，对齐策略需从追求普遍共识转向尊重文化多样性。我们发现，强制密集模型适应冲突的价值分布会导致‘均值坍缩’，即模型收敛至一个泛化平均值，无法体现多元群体特征。这归因于‘文化稀疏性’——梯度干扰使密集参数难以覆盖不同的文化模式。为此，我们提出 extsc{CuMA}（文化专家混合），将对齐视为条件容量分离问题。通过引入人口属性感知的路由机制， extsc{CuMA} 内部构建了潜在文化拓扑，显式将冲突梯度分解至专用专家子空间。在 WorldValuesBench、Community Alignment 与 PRISM 数据集上的大量评估表明， extsc{CuMA} 达到当前最佳性能，显著优于密集基线和仅基于语义的 MoE 模型。关键分析证实， extsc{CuMA} 有效缓解了均值坍缩，保留了文化多样性。代码已开源：https://github.com/Throll/CuMA。
原文摘要 · Abstract (English)
As Large Language Models (LLMs) serve a global audience, alignment must transition from enforcing universal consensus to respecting cultural pluralism. We demonstrate that dense models, when forced to fit conflicting value distributions, suffer from \textbf{Mean Collapse}, converging to a generic average that fails to represent diverse groups. We attribute this to \textbf{Cultural Sparsity}, where gradient interference prevents dense parameters from spanning distinct cultural modes. To resolve this, we propose \textbf{\textsc{CuMA}} (\textbf{Cu}ltural \textbf{M}ixture of \textbf{A}dapters), a framework that frames alignment as a \textbf{conditional capacity separation} problem. By incorporating demographic-aware routing, \textsc{CuMA} internalizes a \textit{Latent Cultural Topology} to explicitly disentangle conflicting gradients into specialized expert subspaces. Extensive evaluations on WorldValuesBench, Community Alignment, and PRISM demonstrate that \textsc{CuMA} achieves state-of-the-art performance, significantly outperforming both dense baselines and semantic-only MoEs. Crucially, our analysis confirms that \textsc{CuMA} effectively mitigates mean collapse, preserving cultural diversity. Our code is available at https://github.com/Throll/CuMA.
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。