LLM社会模拟的蝴蝶效应：从架构敏感性到稳健性审计
原标题：The Butterfly Effect in LLM Social Simulations: From Architecture Sensitivity to Robustness Audits
AI 摘要
该论文研究 LLM 社会模拟中的“蝴蝶效应”：局部实现选择（如人格表示、游戏框架、记忆表示）的扰动会通过智能体交互传播，改变集体结果。作者在重复囚徒困境和社交媒体回音室两类模拟中测试四个 LLM 家族，发现仅改变匹配人格的表示即可使 GPT-5.2 的双人合作率变化若干百分点，且多智能体交互会放大或衰减这种敏感性。论文提出 TRAILS 分类框架和 Social Simulation Audit Card，用于系统审计模拟对实现选择的依赖，并校准科学结论的稳健性范围。
正文节选
redhlbox \tl_set:Ne\greenhlboxgreenhlbox The Butterfly Effect in LLM Social Simulations: From Architecture Sensitivity to Robustness Audits Abstract A butterfly effect occurs when a local perturbation propagates through a system and produces divergence in its collective outcome. In LLM social simulations, this creates a particular challenge for scientific inference: sensitivity to implementation choices can enter agent interactions and alter the collective outcomes on which scientific claims a