arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.08236cs.LGcs.AI
收藏

隐藏的偏见:大型语言模型中显性与隐性政治刻板印象研究

The Hidden Bias: A Study on Explicit and Implicit Political Stereotypes in Large Language Models

Technische Universität Dresden(德累斯顿技术大学);Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI)(可扩展数据与人工智能研究中心(ScaDS.AI))

Konrad Löhr, Shuzhou Yuan, Michael Färber

AI总结:

本研究通过政治罗盘测试评估八个大型语言模型,发现它们普遍左倾,且隐性政治刻板印象比显性更显著,但两者大体一致,揭示了模型对自身偏见的透明度。

摘要:

大型语言模型(LLMs)在信息传播和决策过程中日益不可或缺。鉴于其日益增长的社会影响力,理解潜在偏见,尤其是在政治领域内的偏见,对于防止其对公众舆论和民主进程产生不当影响至关重要。本研究利用二维政治罗盘测试(PCT),调查了八个主流大型语言模型中的政治偏见和刻板印象传播。首先,采用PCT评估这些模型固有的政治倾向。随后,使用PCT进行人物角色提示,以探索不同社会维度上的显性刻板印象。最后一步,通过使用多语言版本的PCT评估模型,揭示隐性刻板印象。关键发现显示,所有被调查模型均呈现一致的左倾政治立场。此外,虽然刻板印象的性质和程度在不同模型间差异显著,但通过语言变化引发的隐性刻板印象比通过显性人物角色提示识别的更为突出。有趣的是,对于大多数模型,隐性和显性刻板印象显示出显著的一致性,表明这些模型对其固有偏见具有一定程度的透明度或“意识”。本研究强调了LLMs中政治偏见与刻板印象之间复杂的相互作用。

英文摘要:

Large Language Models (LLMs) are increasingly integral to information dissemination and decision-making processes. Given their growing societal influence, understanding potential biases, particularly within the political domain, is crucial to prevent undue influence on public opinion and democratic processes. This work investigates political bias and stereotype propagation across eight prominent LLMs using the two-dimensional Political Compass Test (PCT). Initially, the PCT is employed to assess the inherent political leanings of these models. Subsequently, persona prompting with the PCT is used to explore explicit stereotypes across various social dimensions. In a final step, implicit stereotypes are uncovered by evaluating models with multilingual versions of the PCT. Key findings reveal a consistent left-leaning political alignment across all investigated models. Furthermore, while the nature and extent of stereotypes vary considerably between models, implicit stereotypes elicited through language variation are more pronounced than those identified via explicit persona prompting. Interestingly, for most models, implicit and explicit stereotypes show a notable alignment, suggesting a degree of transparency or "awareness" regarding their inherent biases. This study underscores the complex interplay of political bias and stereotypes in LLMs.

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。

↑