研究人与聊天机器人对话中谁在掌控对话，发现控制权是双方轮流构建的。
Does My Chatbot Have an Agenda? Understanding Human and AI Agency in Human-Human-like Chatbot Interaction
- 通过长期对话实验和访谈，观察人类与AI在对话中共同建构控制权。
- 发现对话中人类设边界、AI引导意图，双方动态协作决定走向。
- 提出透明设计建议，适合关注人机交互与对话系统设计的研究者。
随着人工智能聊天机器人从工具转向陪伴角色，关于对话中由谁主导的问题日益重要。本文通过一项为期一个月的纵向研究，让22名成年参与者与我们开发的大型语言模型伴侣Day持续对话，随后进行半结构化访谈，回溯关键对话时刻，跨参与者分析聊天记录，并在‘策略揭示’环节公开Day每轮对话的目标。研究发现，控制权并非单方拥有，而是随着参与者设定边界、AI引导意图而逐步形成的一种共享体验，每一轮对话都在动态共建。为此，我们提出一个3×4框架，按行为类型（意图、执行、适应、限定）与行动者（人类、AI、混合体）分类，受个体与环境因素调节。研究主张采用‘按需透明’的设计理念，为具备自我意识的对话智能体提供设计启示。
原文摘要 · Abstract (English)
As AI chatbots shift from tools to companions, critical questions arise: who controls the conversation in human-AI chatrooms? This paper explores perceived human and AI agency in sustained conversation. We report a month-long longitudinal study with 22 adults who chatted with Day, an LLM companion we built, followed by a semi-structured interview with post-hoc elicitation of notable moments, cross-participant chat reviews, and a 'strategy reveal' disclosing Day's goal for each conversation. We discover agency manifests as an emergent, shared experience: as participants set boundaries and the AI steered intentions, control was co-constructed turn-by-turn. We introduce a 3-by-4 framework mapping actors (Human, AI, Hybrid) by their action (Intention, Execution, Adaptation, Delimitation), modulated by individual and environmental factors. We argue for translucent design (transparency-on-demand) and provide implications for agency self-aware conversational agents.
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。