LLM狼人杀实验：语言风格不影响信任与投票
Language as Trait, Politeness as Strategy: Controlled Tests of Linguistic Effects in LLM Social-Deduction Agents
有人把狼人杀AI的发言改措辞重放了4335次，结果发现礼貌和语言复杂度根本骗不到别的AI，挺反直觉的。
研究基于 LURK Werewolf 框架，把每句话的言语行为谓词和语言实现分开，只改写措辞并从存档检查点重放对局。跨 30 局、4,335 次重放的实验显示，语言复杂度与礼貌策略都不改变其他智能体对发言者的信任，投票和夜晚行动的效应在校正多重比较后均不显著。未校正的最大效应是把语言复杂度从中性改写偏移后，其他玩家投票变化约 4 个百分点。自然对局中，88% 的威胁面子话语都是直陈式，与角色无关。
Language as Trait, Politeness as Strategy: Controlled Tests of Linguistic Effects in LLM Social-Deduction Agents
Large language model (LLM) agents coordinate through conversation, and the same message can be phrased in simpler or more complex language, bluntly or politely. We test whether such differences change how other agents judge and act, using the LURK Werewolf framework, which separates each utterance's speech-act predicate from its natural-language realization. We rewrite only the realization, check that the game content is preserved, and replay each game day from saved checkpoints against a re-sampled control. We vary linguistic range consistently across a speaker's messages and politeness strategy per utterance. Across 30 games and 4,335 replays, neither manipulation changes the trust other agents place in the speaker, and no effect on votes or night actions survives correction for multiple comparisons; the largest uncorrected effect is that shifting range away from a neutral paraphrase changes about 4 percentage points more of the other players' votes. In natural play, 88% of face-threatening speech is bald on-record regardless of role.
