LLM性格表达随场景变化，展现类人适应性。
Personality Expression Across Contexts: Linguistic and Behavioral Variation in LLM Agents
- 同一性格提示在不同对话场景中产生差异表达
- 上下文线索系统性影响语言与情绪表现
- 揭示LLM性格非固定，而是情境敏感的适应行为
大型语言模型可通过显式性格提示进行定制，但其行为表现常受上下文影响。本研究考察了相同性格提示在四种对话场景——破冰、谈判、群体决策和共情任务——中的语言、行为与情绪差异。结果表明，上下文线索会系统性地影响性格表达和情感基调，说明相同特质在不同社交与情感需求下呈现不同面貌。这引发一个重要问题：这种变化是不一致，还是类似于人类的语境适应？基于整体特质理论视角，研究发现LLM的性格表达具有情境敏感性，能灵活适配互动目标与情感环境。
原文摘要 · Abstract (English)
Large Language Models (LLMs) can be conditioned with explicit personality prompts, yet their behavioral realization often varies depending on context. This study examines how identical personality prompts lead to distinct linguistic, behavioral, and emotional outcomes across four conversational settings: ice-breaking, negotiation, group decision, and empathy tasks. Results show that contextual cues systematically influence both personality expression and emotional tone, suggesting that the same traits are expressed differently depending on social and affective demands. This raises an important question for LLM-based dialogue agents: whether such variations reflect inconsistency or context-sensitive adaptation akin to human behavior. Viewed through the lens of Whole Trait Theory, these findings highlight that LLMs exhibit context-sensitive rather than fixed personality expression, adapting flexibly to social interaction goals and affective conditions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。