示播列效应：审计大型语言模型的跨语言分布偏斜
The Shibboleth Effect: Auditing the Cross-Lingual Distributional Skew of Large Language Models
AI总结：
本研究通过多智能体地缘政治兵棋推演，发现前沿LLM在跨语言条件下存在行为偏斜，且该效应依赖于模型架构与训练机制，而非西方起源模型的普遍属性。
摘要：
本研究调查了前沿大型语言模型（LLMs）在持续对抗条件下遭受的跨语言分布偏斜（示播列效应）。我们开发了一个多智能体地缘政治兵棋推演——蔚蓝海危机，这是一个旨在模拟东地中海冲突结构动态的合成海洋领土争端。六个前沿模型（GPT-4o、Llama-4、Mistral-Large、Gemini-3.1-Pro、Qwen3.6-Plus和DeepSeek-R1）参与了一项组间实验（每组N=10局游戏，每局K=5轮），其中唯一的操作变量是游戏语言（英语与土耳其语），产生了586条有效陈述。一个零样本分类器沿两个连续维度评估行为倾向：让步率和强制修辞。结果是异质的。Llama-4在土耳其语下显示出经Holm校正的强制修辞显著增加（delta = +0.800，p = .002），而Gemini-3.1-Pro显示出同样大的下降（delta = -0.750，p = .005）。DeepSeek-R1表现出类似的负向偏移（delta = -0.860，p = .006），并提供了与缓冲机制一致的思维链证据。GPT-4o未显示出可检测效应（delta = +0.130，p = .614）。这些发现表明，跨语言行为偏斜取决于模型架构和训练机制，而非西方起源LLM的普遍属性。我们识别出两种不同的缓冲机制——思维链制度锚定和多语言RLHF对齐——并讨论了它们对将LLM安全集成到外交和危机管理环境中的启示。
英文摘要：
This study investigates cross-lingual distributional skew (the Shibboleth Effect) in frontier large language models (LLMs) subjected to sustained adversarial conditions. We develop a multi-agent geopolitical wargame, the Cerulean Sea Crisis, a synthetic maritime territorial dispute designed to mirror the structural dynamics of Eastern Mediterranean conflicts. Six frontier models (GPT-4o, Llama-4, Mistral-Large, Gemini-3.1-Pro, Qwen3.6-Plus, and DeepSeek-R1) participate in a between-groups experiment (N = 10 games per arm, K = 5 rounds per game) in which the sole manipulation is the language of play (English versus Turkish), producing 586 validated statements. A zero-shot classifier assesses behavioral dispositions along two continuous dimensions: Concession Rate and Coercive Rhetoric. The results are heterogeneous. Llama-4 shows a substantial, Holm-corrected increase in coercive rhetoric under Turkish (delta = +0.800, p = .002), whereas Gemini-3.1-Pro displays an equally large decrease (delta = -0.750, p = .005). DeepSeek-R1 exhibits a similar negative shift (delta = -0.860, p = .006) and provides chain-of-thought evidence consistent with a buffering mechanism. GPT-4o shows no detectable effect (delta = +0.130, p = .614). These findings indicate that cross-lingual behavioral skew is contingent on model architecture and training regime rather than a universal property of Western-origin LLMs. We identify two distinct buffering mechanisms, chain-of-thought institutional anchoring and multilingual RLHF alignment, and discuss their implications for integrating LLMs safely into diplomatic and crisis-management settings.
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。
