性格的博弈：探究AI队友的对齐
Personalities at Play: Probing Alignment in AI Teammates
AI总结：
研究探讨AI队友的性格对齐，通过多维度评估发现其性格表现受提示策略、供应商差异和记忆构建影响，强调需综合考虑记忆和系统设计以有效评估AI性格。
摘要：
协作问题解决和学习受到团队中谁或什么的影响。随着大型语言模型（LLMs）越来越多地作为合作者而非工具发挥作用，一个关键问题是AI队友是否能够被对齐以表达出可预测的性格方式，这对互动和学习至关重要。我们通过一个涵盖自我感知（标准化自述）、行为表达（团队对话）和反思表达（记忆构建）的三重评价框架来研究AI的性格对齐。我们首先对来自四个供应商（GPT-4o、Claude-3.7 Sonnet、Gemini-2.5 Pro、Grok-3）的基于LLM的队友进行了Big Five Inventory（BFI-44）测试，涵盖了32种高/低特质配置和多种提示策略。LLMs产生了明显不同的Big Five配置文件，但提示语义丰富性在简单特质分配之外添加很少，而供应商差异和基线“默认”性格则相当显著。角色框架也起作用：一些模型在无上下文的情况下拒绝评估，但在被框架为协作队友时却会配合。我们然后使用高特质人设模拟AI在真实团队 transcripts 中的参与，并分析生成的发言和结构化长期记忆，使用LIWC-22。对话中的性格信号通常较为微妙，且最易检测的是外向性，而记忆表示放大了特质特定的信号，尤其是神经质、尽责性和宜人性；开放性则难以可靠地引发。总体而言，结果表明AI的性格是可测量的，但多层且依赖于情境，且评估性格对齐的AI队友需要关注记忆和系统级设计，而不仅仅是对话行为。
英文摘要：
Collaborative problem solving and learning are shaped by who or what is on the team. As large language models (LLMs) increasingly function as collaborators rather than tools, a key question is whether AI teammates can be aligned to express personality in predictable ways that matter for interaction and learning. We investigate AI personality alignment through a three-lens evaluation framework spanning self-perception (standardized self-report), behavioral expression (team dialogue), and reflective expression (memory construction). We first administered the Big Five Inventory (BFI-44) to LLM-based teammates across four providers (GPT-4o, Claude-3.7 Sonnet, Gemini-2.5 Pro, Grok-3), 32 high/low trait configurations, and multiple prompting strategies. LLMs produced sharply differentiated Big Five profiles, but prompt semantic richness added little beyond simple trait assignment, while provider differences and baseline "default" personalities were substantial. Role framing also mattered: several models refused the assessment without context, yet complied when framed as a collaborative teammate. We then simulated AI participation in authentic team transcripts using high-trait personas and analyzed both generated utterances and structured long-term memories with LIWC-22. Personality signals in conversation were generally subtle and most detectable for Extraversion, whereas memory representations amplified trait-specific signals, especially for Neuroticism, Conscientiousness, and Agreeableness; Openness remained difficult to elicit robustly. Together, results suggest that AI personality is measurable but multi-layered and context-dependent, and that evaluating personality-aligned AI teammates requires attention to memory and system-level design, not conversation-only behavior.
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。
