Cross-Lingual Persona Effects in LLM Negotiation

Computer Science > Computation and Language arXiv:2611.00300 (cs) [Submitted on 30 Oct 2026] Title: Cross-Lingual Persona Effects in LLM Negotiation Authors: Saehee Eom, Tejas Khandwekar.

计算机科学 > 计算与语言 arXiv:2611.00300 (cs) [提交于 2026 年 10 月 30 日] 标题：大语言模型谈判中的跨语言人格效应 作者：Saehee Eom, Tejas Khandwekar。

Abstract: Tell an LLM negotiator to be “headstrong” and it should hold firm on price, but does that instruction retain the same behavior in every language? To test this, we use identical buyer and seller instances of Gemini 3.6 Flash to negotiate the same 12 CraigslistBargain scenarios in English and Korean. The pilot-scale 2 x 2 x 3 design crosses interaction language, seller urgency (none or strong), and buyer persona (cooperative, neutral, or headstrong), yielding 432 attempted negotiations.

摘要：告诉大语言模型（LLM）谈判者要“固执”，它应该在价格上坚持立场，但这一指令在每种语言中是否都能保持相同的行为？为了测试这一点，我们使用相同的 Gemini 3.6 Flash 买家和卖家实例，在英语和韩语中对相同的 12 个 CraigslistBargain 场景进行谈判。这项试点规模的 2 x 2 x 3 设计交叉了交互语言、卖家紧迫性（无或强）以及买家性格（合作、中立或固执），共进行了 432 次谈判尝试。

We call this property cross-lingual social-policy fidelity: whether a prompt-defined social policy produces the same behavioral effect regardless of interaction language. It often does not. Korean negotiations reached agreement far more often than English (77.3% vs. 52.5%, a 24.8-point gap, Holm-adjusted p = .0039), but only for neutral and headstrong buyers; cooperative buyers were already near-ceiling in both languages.

我们将这种属性称为跨语言社会政策保真度：即提示词定义的社会政策是否在不考虑交互语言的情况下产生相同的行为效果。事实往往并非如此。韩语谈判达成协议的频率远高于英语（77.3% 对 52.5%，差距为 24.8 个百分点，Holm 校正 p = .0039），但这仅限于中立和固执的买家；合作型买家在两种语言中都已经接近上限。

Buyers’ opening offers barely differed by language; the gap instead emerged later, through larger seller concessions and a smaller final gap in Korean, and agreed prices were also lower in Korean. Repeating the full design with Qwen3.7 Flash as both agents gives directional support: agreement was again higher in Korean (+13.9 points vs. Gemini’s +24.8, with an interval whose lower bound is near zero), and sellers again conceded more.

买家的开盘报价在不同语言间几乎没有差异；差距反而在后期显现，表现为韩语中卖家做出了更大的让步，最终差距更小，且韩语中的成交价格也更低。使用 Qwen3.7 Flash 作为双方代理重复整个设计提供了方向性支持：韩语中的协议达成率再次更高（+13.9 个百分点，对比 Gemini 的 +24.8，其区间的下限接近于零），且卖家再次做出了更多让步。

Pragmatic analysis reveals why: while both languages frequently featured face-threatening acts like rejections and counter-offers, Korean dialogue softened these threats with substantially more politeness mitigation, especially among sellers (11.7% vs. 3.6%). These results show that such a policy can produce different simulated negotiation behavior, not just different wording, when only the interaction language changes.

语用分析揭示了原因：虽然两种语言都频繁出现拒绝和还价等威胁面子的行为，但韩语对话通过更多的礼貌缓和措施减轻了这些威胁，尤其是在卖家群体中（11.7% 对 3.6%）。这些结果表明，当仅改变交互语言时，此类政策不仅会产生不同的措辞，还会产生不同的模拟谈判行为。