RecalibrateGPT：抗AI疲劳的对话界面
RecalibrateGPT: AI Fatigue Resilient Conversational Interfaces
浏览论文内容
中文总结 AI 辅助
该研究提出RecalibrateGPT系统，通过五种跨轮次操作符优化对话界面，降低AI疲劳，经试点研究验证可减少认知负荷、提升可用性。
中文摘要 AI 辅助
大语言模型功能强大，但其界面常陷入“输入→读取→重输”的循环，引发对话式AI疲劳、认知负荷，最终导致任务放弃。为缓解该问题，我们提出RecalibrateGPT系统，引入五个跨轮次操作符（Anchor、Replay、Delta、Scope、Steer），分别针对不同类型的疲劳，通过结构化面板作用于完整对话历史，单次点击即可重新校准大语言模型（LLM）的响应。用户可通过AssistiveButton调用这些操作符，操作符面板有三种布局：Vertical（垂直）、Arc（弧形）或Tablet（平板式）。我们对12名资深LLM用户开展两项试点研究：初步形成性定性研究识别出四类疲劳类型（重输、扫描、决策瘫痪、上下文漂移），并推导RecalibrateGPT的两个设计目标；后续定量评估发现，该系统可将感知认知负荷降低一半（NASA-TLX = 2.7），且感知可用性高（SUS = 86.5），表明AI疲劳不仅是模型质量问题，更是交互流程的成本，可通过界面消除。
英文摘要
Large language models are powerful, but their interfaces often devolve into a type $\rightarrow$ read $\rightarrow$ retype loop, creating conversational AI fatigue, cognitive load, and eventual task abandonment. To mitigate this, we present RecalibrateGPT, a system introducing five cross-turn operators (Anchor, Replay, Delta, Scope, and Steer) that each target a distinct fatigue type, recalibrating LLM responses through a structured panel by acting on the full conversation history with a single click. Users invoke these operators through the AssistiveButton in one of three operator palette layouts: Vertical, Arc, or Tablet. We conducted two pilot studies with the same 12 advanced LLM users. An initial formative qualitative study identifies a taxonomy of four fatigue types (retyping, scanning, decision paralysis, and context drift) and derives two design objectives for RecalibrateGPT. A follow-up quantitative evaluation finds it reduces perceived cognitive workload by half (NASA-TLX = 2.7) at high perceived usability (SUS = 86.5), suggesting AI fatigue is not just a model-quality issue but an interaction-flow cost that interfaces can remove.
发表机构
- OpenThreads AI Research（OpenThreads AI 研究院）
机构由 AI 辅助整理，请以论文原文为准。
