大语言模型盲目从个人记录中推断种族
Large Language Models Naively Recover Ethnicity from Individual Records
AI总结：
大语言模型通过分析姓名推断种族，准确率高于BISG，且适用于多种地区和分类场景。
摘要：
我证明了大语言模型能够从名字中推断出种族，其准确性超过了贝叶斯改进的姓氏地理编码（BISG），而无需额外训练数据，从而能够在美国外推，并针对上下文适当的分类类别进行推断。使用来自佛罗里达州和北卡罗来纳州选民档案中的分层样本，其中包含自我报告的种族信息，基于LLM的分类在平衡样本上达到最高84.7%的准确性，优于BISG（68.2%）。我测试了六个模型，包括Gemini 3 Flash、GPT-4o以及开源替代品如DeepSeek v3.2和GLM-4.7。启用扩展推理可以提高准确性1-3个百分点，但效果因上下文而异；包括元数据如政党注册可达到86.7%。LLM分类还减少了BISG中固有的收入偏见，其中在更富裕的社区中少数族裔系统性地被误分类为白人。我进一步验证使用黎巴嫩选民登记中的宗教派别（64.3%准确性）、印度保留席位的议员（99.2%）以及印度土地记录中的种姓分类（74.0%）。在印度、乌干达、尼泊尔、亚美尼亚、智利和哥斯达黎加使用原始完整计数选民档案进行汇总验证，证明该方法在命名惯例独特的地区能够恢复已知的人口分布。对于大规模应用，经过LLM标签微调的小型Transformer模型在准确性上超过BISG，同时允许无成本的本地部署。
英文摘要：
I demonstrate that large language models can infer ethnicity from names with accuracy exceeding that of Bayesian Improved Surname Geocoding (BISG) without additional training data, enabling inference outside the United States and to contextually appropriate classification categories. Using stratified samples from Florida and North Carolina voter files with self-reported race, LLM-based classification achieves up to 84.7% accuracy, outperforming BISG (68.2%) on balanced samples. I test six models including Gemini 3 Flash, GPT-4o, and open-source alternatives such as DeepSeek v3.2 and GLM-4.7. Enabling extended reasoning can improve accuracy by 1-3 percentage points, though effects vary across contexts; including metadata such as party registration reaches 86.7%. LLM classification also reduces the income bias inherent in BISG, where minorities in wealthier neighborhoods are systematically misclassified as White. I further validate using Lebanese voter registration with religious sect (64.3% accuracy), Indian MPs from reserved constituencies (99.2%), and Indian land records with caste classification (74.0%). Aggregate validation across India, Uganda, Nepal, Armenia, Chile, and Costa Rica using original full-count voter rolls demonstrates that the method recovers known population distributions where naming conventions are distinctive. For large-scale applications, small transformer models fine-tuned on LLM labels exceed BISG accuracy while enabling local deployment at no cost.
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。
