大语言模型智能体能否在对话中保持角色一致性？
Can LLM Agents Maintain a Persona in Discourse?
AI总结：
针对LLMs对话智能体存在的人格一致性缺失问题，通过构建OCEAN框架人格的二元对话并利用评判智能体分析，发现其人格保持能力受模型组合与对话设置影响显著，凸显人格对齐交互的挑战。
摘要：
大语言模型（LLMs）被广泛用作对话智能体，在教育、法律、医学等多个领域发挥其能力。然而，LLMs常表现出语境转换行为，导致缺乏一致且可解释的人格对齐交互。对心理特质的遵循缺乏全面分析，尤其是在二元（成对）对话场景中。我们从两个视角研究这一挑战：首先使用两个对话智能体就某一主题生成对话，每个智能体被赋予OCEAN框架（开放性、尽责性、外向性、宜人性、神经质）中的高/低人格特质；随后使用多个评判智能体推断分配的原始特质，以探究预测一致性、模型间一致性及与分配人格的对齐性。研究结果表明，尽管LLMs可被引导进行人格驱动的对话，但其保持人格特质的能力因模型组合和对话设置的不同而存在显著差异。这些不一致性凸显了在LLMs中实现稳定且可解释的人格对齐交互所面临的挑战。
英文摘要：
Large Language Models (LLMs) are widely used as conversational agents, exploiting their capabilities in various sectors such as education, law, medicine, and more. However, LLMs are often subjected to context-shifting behaviour, resulting in a lack of consistent and interpretable personality-aligned interactions. Adherence to psychological traits lacks comprehensive analysis, especially in the case of dyadic (pairwise) conversations. We examine this challenge from two viewpoints, initially using two conversation agents to generate a discourse on a certain topic with an assigned personality from the OCEAN framework (Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism) as High/Low for each trait. This is followed by using multiple judge agents to infer the original traits assigned to explore prediction consistency, inter-model agreement, and alignment with the assigned personality. Our findings indicate that while LLMs can be guided toward personality-driven dialogue, their ability to maintain personality traits varies significantly depending on the combination of models and discourse settings. These inconsistencies emphasise the challenges in achieving stable and interpretable personality-aligned interactions in LLMs.
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。
