揭示大模型对主流意识形态的隐性偏移及其社会影响
Propaganda is all you need
- 从政治哲学视角分析大模型对齐机制如何塑造语义空间
- 发现多数大模型嵌入空间呈现马克思主义所说的'主导意识形态'
- 警示模型在公共决策中可能加剧社会同质化或助长极端思想
由于机器学习仍是相对较新的研究领域，尤其在数学与计算机科学之外，关于大型语言模型（LLMs）政治维度的研究寥寥无几，尤其是对对齐过程的政治面向。该过程既可简单如提示工程，也可能极为复杂，并深刻影响无关概念。例如，政治导向的对齐会显著改变大模型的嵌入空间，重塑政治概念间的相对位置。通过专门工具评估普遍政治偏见并分析对齐影响，我们能获取新数据以理解其成因及对社会的潜在后果。采用社会政治视角，我们假设大多数大型语言模型均与马克思主义所称的‘主导意识形态’保持一致。随着人工智能在公民层面乃至政府机构中的政治决策中扮演日益重要的角色，此类偏差可能引发巨大社会影响，既可能催生新型、隐蔽的社会一致性路径，也可能使伪装的极端观点获得公众广泛传播。
原文摘要 · Abstract (English)
As Machine Learning (ML) is still a recent field of study, especially outside the realm of abstract Mathematics and Computer Science, few works have been conducted on the political aspect of large Language Models (LLMs), and more particularly about the alignment process and its political dimension. This process can be as simple as prompt engineering but is also very complex and can affect completely unrelated notions. For example, politically directed alignment has a very strong impact on an LLM's embedding space and the relative position of political notions in such a space. Using special tools to evaluate general political bias and analyze the effects of alignment, we can gather new data to understand its causes and possible consequences on society. Indeed, by taking a socio-political approach, we can hypothesize that most big LLMs are aligned with what Marxist philosophy calls the 'dominant ideology.' As AI's role in political decision-making, at the citizen's scale but also in government agencies, such biases can have huge effects on societal change, either by creating new and insidious pathways for societal uniformity or by allowing disguised extremist views to gain traction among the people.
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。