AI 人格、服务消费与用户意图熵：来自 LLM 平台的田野实验证据
AI Persona, Service Consumption, and User Intent Entropy: Field Experimental Evidence from an LLM Platform
另 1 家 · 查看机构详情
- Zhejiang University（浙江大学）
- National University of Singapore（新加坡国立大学）
- Dartmouth College（达特茅斯学院）
- Singapore Sapiens Technology Pte. Ltd.（新加坡智人科技有限公司）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
本研究通过田野实验发现，LLM 平台的关系型 AI 人格能显著增加用户互动和产出，但效果因用户意图而异，提示企业应将人格作为运营杠杆并分别评估互动与产出。
中文摘要 AI 辅助
问题定义：部署大语言模型服务的企业必须决定其 AI 如何沟通，而不仅仅是它能做什么。我们考察了关系型人格——比非关系型人格更温暖、更具同理心、更具参与感——如何影响服务消费和用户目标的演变。方法/结果：在一项针对 9,586 名新注册用户的随机田野实验中，我们保持底层模型和服务能力不变。关系型人格增加了互动（会话次数，+8.1%；时长，+10.6%；聊天轮次，+24.2%；意图熵，+5.8%）和产出（文件，+12.3%；不同目标，+12.1%）。效果因进入意图而异。对于任务执行型用户，首次会话效果不显著。社交型和知识探索型用户在聊天轮次上表现出相似的增加：社交型增加了意图熵但没有增加产出，而知识探索型增加了产出但没有提高意图熵。将意图动态建模为转移过程，我们发现社交型的意图转移熵更高（+11.8%），而知识探索型的意图延续概率更高（+12.8%），分别表明更大的对话广度和持久性。在后续使用中，关系型人格增加了所有进入意图下的总聊天轮次和产出。任务执行型的会话次数增加了 12.2%，社交型增加了 49.4%，但知识探索型不显著。对会话次数和意图熵的效果随时间增强，而产出效果保持稳定。管理启示：AI 人格是一个运营设计杠杆，而不仅仅是展示特征。因为更多的互动并不统一地产生更多的产出，企业应分别评估互动和产出，并考虑将人格与用户意图匹配，尤其是当增加的互动消耗昂贵的计算资源时。
英文摘要
Problem definition: Firms deploying large language model services must decide how their AI communicates, not just what it can do. We examine how a relational persona - warmer, more empathetic and more engaging than a non-relational persona - affects service consumption and the evolution of user objectives. Methodology/results: In a randomized field experiment with 9,586 newly registered users, we hold the underlying model and service capabilities constant. The relational persona increases interactions (sessions, +8.1%; duration, +10.6%; chat rounds, +24.2%; intent entropy, +5.8%) and outputs (files, +12.3%; distinct goals, +12.1%). Effects vary by entry intent. First-session effects are insignificant for Task Execution users. Socialization and Knowledge Exploration users show similar increases in chat rounds: Socialization increases intent entropy without more outputs, whereas Knowledge Exploration increases outputs without higher intent entropy. Modeling intent dynamics as a transition process, we find higher intent transition entropy for Socialization (+11.8%) but higher intent continuation probability for Knowledge Exploration (+12.8%), suggesting greater conversational breadth and persistence, respectively. In subsequent use, the relational persona increases aggregate chat rounds and outputs across all entry intents. Session count rises by 12.2% for Task Execution and 49.4% for Socialization, but not significantly for Knowledge Exploration. Effects on session count and intent entropy strengthen over time, whereas output effects remain stable. Managerial implications: AI persona is an operational design lever, not merely a presentation feature. Because more interactions do not uniformly generate more outputs, firms should evaluate interactions and outputs separately and consider matching persona to user intent, especially when added interactions consume costly computing resources.
