大模型
arxiv.org ·
AI 人设、服务消费与用户意图熵：来自 LLM 平台的现场实验证据
该 arXiv 论文以 9586 名新注册用户为样本开展随机现场实验，在底层模型与服务能力保持不变的条件下，考察更温暖、更具共情的关系型 AI 人设对服务消费和用户目标演变的影响。结果显示关系型人设提升交互量（会话 +8.1%、时长 +10.6%、对话轮次 +24.2%、意图熵 +5.8%）与产出（文件 +12.3%、不同目标 +12.1%），且效应因进入意图而异：任务执行用户首轮效应不显著，社交用户意图熵上升但产出未增，知识探索用户产出上升而意图熵未升。作者据此提出 AI 人设是可运营的设计杠杆，企业应分别评估交互与产出，并在交互消耗昂贵算力时考虑人设与用户意图的匹配。
AI推荐理由 arXiv 预印本，基于 9586 名新注册用户的随机现场实验，在模型与服务能力不变的前提下比较关系型人设与非关系型人设的影响，报告了会话数 +8.1%、时长 +10.6%、对话轮次 +24.2%、意图熵 +5.8%、文件产出 +12.3% 等具体效应，并按任务执行、社交、知识探索三类进入意图分层，指出交互增加并不均匀带来产出增加。证据为单一平台现场实验、尚未经同行评审，效果外推需谨慎；但对 AI 产品人设设计与算力成本权衡有直接参考价值。
78
正文
Computer Science > Human-Computer Interaction
arXiv:2609.23274 (cs)
[Submitted on 20 Sep 2026]
Title:AI Persona, Service Consumption, and User Intent Entropy: Field Experimental Evidence from an LLM Platform
Authors:Junjie Li, Xiaofan Li, Lauren Xiaoyuan Lu, Yiwei Wang, Bruce Yang
View a PDF of the paper titled AI Persona, Service Consumption, and User Intent Entropy: Field Experimental Evidence from an LLM Platform, by Junjie Li and 4 other authors
View PDF
Abstract: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.
Subjects:
Human-Computer Interaction (cs.HC)
Cite as:
arXiv:2609.23274 [cs.HC]
(or
arXiv:2609.23274v1 [cs.HC] for this version)
https://doi.org/10.48550/arXiv.2609.23274
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Yiwei Wang [view email]
[v1]
Sun, 20 Sep 2026 01:08:56 UTC (4,868 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled AI Persona, Service Consumption, and User Intent Entropy: Field Experimental Evidence from an LLM Platform, by Junjie Li and 4 other authors
View PDF
view license
Current browse context:
cs.HC
new
|
recent
| 2026-09
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)