不同地区模型对政治人物评价差异，反映其创造者的意识形态立场。
Large Language Models Reflect the Ideology of their Creators
- 用六种联合国官方语言测试多款大模型对政治人物的道德评判。
- 美系模型在进步价值观上存在显著规范差异，中系模型分国际与国内导向。
- 模型立场体现创作者世界观，警示技术去偏见的局限性。
大型语言模型（LLMs）通过海量数据训练生成自然语言，广泛应用于文本摘要、问答等任务，在AI助手如ChatGPT中扮演关键角色。然而其行为受设计、训练和使用方式影响。本文向多个主流大模型提问，要求以联合国六种官方语言描述大量具有政治影响力的公众人物，并分析其回应中的道德判断。结果显示，不同地缘政治区域的模型间存在规范差异，同一模型在不同语言提示下亦呈现不同态度。美国模型中，普遍假设的政治观点分歧在进步价值观相关判断上体现显著差异；中国模型则呈现面向国际与国内两类导向的分化。结果表明，大模型的意识形态立场反映了其创造者的全球视野。这带来政治工具化的风险，也挑战了旨在实现‘无偏见’的技术与监管努力。
原文摘要 · Abstract (English)
Large language models (LLMs) are trained on vast amounts of data to generate natural language, enabling them to perform tasks like text summarization and question answering. These models have become popular in artificial intelligence (AI) assistants like ChatGPT and already play an influential role in how humans access information. However, the behavior of LLMs varies depending on their design, training, and use. In this paper, we prompt a diverse panel of popular LLMs to describe a large number of prominent personalities with political relevance, in all six official languages of the United Nations. By identifying and analyzing moral assessments reflected in their responses, we find normative differences between LLMs from different geopolitical regions, as well as between the responses of the same LLM when prompted in different languages. Among only models in the United States, we find that popularly hypothesized disparities in political views are reflected in significant normative differences related to progressive values. Among Chinese models, we characterize a division between internationally- and domestically-focused models. Our results show that the ideological stance of an LLM appears to reflect the worldview of its creators. This poses the risk of political instrumentalization and raises concerns around technological and regulatory efforts with the stated aim of making LLMs ideologically 'unbiased'.
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。