通过人格分歧实现无训练的文化对齐大语言模型
Training-Free Cultural Alignment of Large Language Models via Persona Disagreement
AI总结：
本文提出DISCA方法，在不改变模型权重的情况下，通过人格分歧校准减少大语言模型在多任务测试中的文化偏差，为服务全球道德偏好提供了可扩展的替代方案。
摘要：
大型语言模型越来越多地参与涉及道德判断的决策，但越来越多的证据表明，它们的隐含偏好并非文化中立。现有的文化对齐方法要么需要国家层面的偏好数据和微调预算，要么假设可以访问模型内部的白盒信息，而商业API并未暴露此类信息。在本工作中，我们专注于这种现实的黑盒、仅公共数据的环境，并观察到国家内部的社会人口学分歧，而非共识，是主要的指导信号。我们引入DISCA（基于分歧的文化对齐推理方法），一种在推理时的方法，将每个国家视为一个基于世界价值观调查的个人代理面板，并将他们的分歧转化为一个有界的、损失厌恶的logit校正。在20个国家和7个开放权重的backbone（2B-70B）上，DISCA在MultiTP上减少了10-24%的文化偏差（在六个backbone >=3.8B上），并在开放场景中减少了2-7%的偏差，而无需改变任何权重。我们的结果表明，推理时的校准是微调的可扩展替代方案，用于服务全球道德偏好的长尾。
英文摘要：
Large language models increasingly mediate decisions that turn on moral judgement, yet a growing body of evidence shows that their implicit preferences are not culturally neutral. Existing cultural alignment methods either require per-country preference data and fine-tuning budgets or assume white-box access to model internals that commercial APIs do not expose. In this work, we focus on this realistic black-box, public-data-only regime and observe that within-country sociodemographic disagreement, not consensus, is the primary steering signal. We introduce DISCA (Disagreement-Informed Steering for Cultural Alignment), an inference-time method that instantiates each country as a panel of World-Values-Survey-grounded persona agents and converts their disagreement into a bounded, loss-averse logit correction. Across 20 countries and 7 open-weight backbones (2B--70B), DISCA reduces cultural misalignment on MultiTP by 10--24% on the six backbones >=3.8B, and 2--7% on open-ended scenarios, without changing any weights. Our results suggest that inference-time calibration is a scalable alternative to fine-tuning for serving the long tail of global moral preferences.
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。
