LLM智能体交互：测量交互式大语言模型群体中的人格一致性与语言对齐
LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models
AI总结：
本研究通过提示为GPT-3.5设定人格画像，构建两组LLM智能体群体，经人格测试与协作写作任务，发现不同画像在人格一致性与语言对齐上存在差异，为理解LLM对话交互及构建类人人格奠定基础。
摘要：
虽然智能体交互和个性化都是大语言模型（LLM）研究中的热门话题，但关于语言交互对基于人格条件的LLM智能体行为影响的研究却十分有限。这一研究对于确保智能体既保持其被赋予的特质一致性，又能参与开放、自然的对话至关重要。在我们的实验中，我们通过提示将GPT-3.5置于人格画像条件下，并使用一种简单的可变性诱导采样算法创建了一个由两组LLM智能体组成的群体。随后，我们进行人格测试，并让智能体参与一项协作写作任务，发现不同画像在与对话伙伴的互动中表现出不同程度的人格一致性和语言对齐。我们的研究旨在为更好地理解LLM之间基于对话的交互奠定基础，并强调需要新方法来为交互环境构建稳健、更类人的LLM人格。
英文摘要：
While both agent interaction and personalisation are vibrant topics in research on large language models (LLMs), there has been limited focus on the effect of language interaction on the behaviour of persona-conditioned LLM agents. Such an endeavour is important to ensure that agents remain consistent to their assigned traits yet are able to engage in open, naturalistic dialogues. In our experiments, we condition GPT-3.5 on personality profiles through prompting and create a two-group population of LLM agents using a simple variability-inducing sampling algorithm. We then administer personality tests and submit the agents to a collaborative writing task, finding that different profiles exhibit different degrees of personality consistency and linguistic alignment to their conversational partners. Our study seeks to lay the groundwork for better understanding of dialogue-based interaction between LLMs and highlights the need for new approaches to crafting robust, more human-like LLM personas for interactive environments.
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。
