Skip to main content
QUICK REVIEW

[论文解读] From Fixed to Flexible: Shaping AI Personality in Context-Sensitive Interaction

Shakyani Jayasiriwardene, Hongyu Zhou|arXiv (Cornell University)|Jan 13, 2026
Social Robot Interaction and HRI被引用 0
一句话总结

论文提出一个实时、用户驱动的系统,允许用户在三个任务情境中在八个维度上调整AI聊天机器人性格,并分析个性化的预期与轨迹如何形成。

ABSTRACT

Conversational agents are increasingly expected to adapt across contexts and evolve their personalities through interactions, yet most remain static once configured. We present an exploratory study of how user expectations form and evolve when agent personality is made dynamically adjustable. To investigate this, we designed a prototype conversational interface that enabled users to adjust an agent's personality along eight research-grounded dimensions across three task contexts: informational, emotional, and appraisal. We conducted an online mixed-methods study with 60 participants, employing latent profile analysis to characterize personality classes and trajectory analysis to trace evolving patterns of personality adjustment. These approaches revealed distinct personality profiles at initial and final configuration stages, and adjustment trajectories, shaped by context-sensitivity. Participants also valued the autonomy, perceived the agent as more anthropomorphic, and reported greater trust. Our findings highlight the importance of designing conversational agents that adapt alongside their users, advancing more responsive and human-centred AI.

研究动机与目标

  • 研究在不同任务条件下,用户如何形成对话式AI个性的预期。
  • 检验在具备情境敏感互动且个性可动态调整的情境中,用户的预期如何演变。
  • 评估 enabling 实时个性调整界面的用户感知。
  • 描述跨情境的基线性格偏好与调整模式。
  • 理解情感拟人性在信任与互动质量中的作用。

提出的方法

  • 开发了一个基于 GPT-4.1 的聊天机器人,具备八个维度的实时个性调节:Decency、Profoundness、Instability、Vibrancy、Engagement、Neuroticism、Serviceability、Subservience。
  • 为每个维度实现五点滑块,每次对话轮只允许一个维度发生变化以隔离效应。
  • 使用结构化系统提示将滑块数值转化为聊天机器人回应。
  • 采用基于 Cutrona and Suhr (1992) 的三种任务情境(Informational、Emotional、Appraisal),结合 GPT-4.1 生成情景。
  • 从60名参与者在线收集混合方法数据,包括自我报告和互动日志。
  • 应用潜在剖面分析(LPA)在每个条件和阶段识别个性配置类别,并用桑基图可视化转变。
  • 使用K-means聚类进行轨迹分析,以识别调整策略(Steady Anchors、Adaptive Explorers、Reactive Shifters)。
  • 通过任务后调查分析特质重要性,并生成各情境净变化热力图。
Figure 1 . The main conversational interface. (A) Slider panel for configuring and fine-tuning the agent’s personality across eight dimensions. (B) Conversational area for task-based interaction with the agent. (C) Information panel providing step-by-step instructions and guidance for using the inte
Figure 1 . The main conversational interface. (A) Slider panel for configuring and fine-tuning the agent’s personality across eight dimensions. (B) Conversational area for task-based interaction with the agent. (C) Information panel providing step-by-step instructions and guidance for using the inte

实验结果

研究问题

  • RQ1RQ1:在不同任务条件下,用户如何基于对话AI形成个性预期?
  • RQ2RQ2:在情境敏感的对话中,用户对话AI个性的预期如何动态演化?
  • RQ3RQ3:用户如何看待具备动态可调个性的对话AI界面?

主要发现

  • 用户预期因情境而异,与不同社会角色(例如助手、向导、协助者)趋同。
  • 在所有情境中,Engagement与Serviceability为基线偏好;Decency在评估情境中特别显著。
  • 在各情境中,参与者趋向于共同关注的特质(Engagement、Serviceability),并表达对细微调节维度的需求。
  • 观察到三种调整轨迹:Steady Anchors、Adaptive Explorers、Reactive Shifters,且在不同情境下的流行度各异。
  • 特质调整中,Engagement与Decency变化最小,而Neuroticism、Subservience、Instability则呈现更多波动。
  • 情感拟人性有助于在自适应界面中提升对信任的感知,同时也与胜任力并存。
Figure 2 . Overview of the user study procedure, from consent and pre-task measures through task-based chatbot interactions, post-task surveys, and post-study questionnaire.
Figure 2 . Overview of the user study procedure, from consent and pre-task measures through task-based chatbot interactions, post-task surveys, and post-study questionnaire.

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。