CuMA: 通过人口统计感知的适配器混合使大语言模型与稀疏文化价值观对齐
CuMA: Aligning LLMs with Sparse Cultural Values via Demographic-Aware Mixture of Adapters
AI总结：
提出CuMA框架，通过人口统计感知路由将冲突梯度分离到专家子空间，解决密集模型在多文化对齐中的均值崩溃问题，在WorldValuesBench等基准上取得最优性能。
摘要：
随着大语言模型服务于全球用户，对齐必须从强制执行普遍共识转向尊重文化多元主义。我们证明，密集模型在被迫适应冲突的价值分布时会出现\textbf{均值崩溃}，收敛到无法代表不同群体的通用平均值。我们将其归因于\textbf{文化稀疏性}，其中梯度干扰阻止密集参数跨越不同的文化模式。为解决此问题，我们提出\textbf{\textsc{CuMA}}（\textbf{Cu}ltural \textbf{M}ixture of \textbf{A}dapters），一个将对齐视为\textbf{条件容量分离}问题的框架。通过引入人口统计感知路由，\textsc{CuMA}内化了一个\textit{潜在文化拓扑}，以将冲突梯度明确解耦到专门的专家子空间中。在WorldValuesBench、Community Alignment和PRISM上的广泛评估表明，\textsc{CuMA}达到了最先进的性能，显著优于密集基线和仅语义MoE。关键的是，我们的分析证实\textsc{CuMA}有效缓解了均值崩溃，保留了文化多样性。我们的代码可在该https URL获取。
英文摘要：
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.
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。
