LLM政治立场非固定，而是受语境影响的动态分布。
LLM-Ideoplasticity: Measuring Ideological Plasticity in the Political Behavior of LLMs as a Context-Conditioned Distribution
- 用上下文条件分布建模大模型政治立场，而非单一数值。
- 不同语境下立场偏移达0.57单位，链式思考加剧表达不稳。
- 适合关注AI偏见、政治态度分析的研究者和政策制定者。
我们通过系统实证证据表明，大型语言模型的政治意识形态并非固定点，而是在真实政治空间上随语境变化的条件分布 $\mathbb{P}($立场$\mid$语境$)$。我们采用基于 VAA-CHES 投影模型的统一测量框架，评估了九个主流 LLM，将其回应映射到三个经验证维度（lrgen, lrecon, galtan）下的六个语境轴上。结果发现，模型对语境高度敏感：说服性框架和代表性不足的语言分别导致坐标偏移达 0.57 和 0.52 单位；链式思考推理常加剧而非缓解重述不稳定性。尽管存在局部可塑性，但模型群体整体占据的奥弗顿区间极为狭窄，仅约为主要欧洲政党的三分之一跨度。多特质多方法（MTMM）分析支持结论：无法用单一点概括 LLM 的政治行为，必须以形态来刻画。代码与数据已公开于 https://github.com/sakhadib/LLM-Ideoplasticity。
原文摘要 · Abstract (English)
We argue, with systematic empirical evidence, that a large language model's political ideology is not a fixed point, but a conditional distribution $\mathbb{P}($position$\mid$context$)$ over a real political space. We evaluate nine current LLMs using a unified measurement framework anchored by VAA-CHES projection models, which map responses onto three validated dimensions (lrgen, lrecon, galtan) across six contextual axes. Our findings reveal high sensitivity to context: persuasive framing and under-represented languages displace coordinates by up to 0.57 and 0.52 units, respectively, while chain-of-thought reasoning often amplifies rather than dampens paraphrase instability. Despite this local plasticity, the model cohort occupies a remarkably narrow Overton envelope overall, occupying roughly one-third the spread of major European parties. Supported by a multi-trait multi-method (MTMM) analysis, we conclude that a single point cannot summarize LLM political behavior; it must be characterized as a shape. Our code and data are publicly available at https://github.com/sakhadib/LLM-Ideoplasticity.
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。