让大模型更像人，但要可控地设计人性特征。
Humanizing Machines: Rethinking LLM Anthropomorphism Through a Multi-Level Framework of Design
- 从感知、语言、行为、认知四维度设计人性化线索
- 提出可操作的框架，指导如何有目的地塑造模型人格
- 适合想提升人机交互体验的设计师和开发者
大型语言模型（LLMs）正越来越多地表现出拟人化特征——在外观、语言、行为和推理功能上呈现出类人特质。这些特征使人机交互更加直观且富有吸引力。然而，当前对拟人化的研究仍以风险为导向，强调过度信任与用户欺骗，缺乏具体的设计指引。本文主张将拟人化视为一种可调控的设计概念，应根据用户目标进行有意调整。基于多学科视角，我们提出：大模型产物的拟人化体现的是设计者与使用者之间的互动，这种互动由设计者嵌入的线索与使用者的认知反应共同促成。线索分为四个维度：感知、语言、行为和认知。通过分析各类线索的表现与效果，我们构建了一个统一的分类体系，并为实践者提供可操作的设计杠杆。因此，我们倡导以功能为导向评估拟人化设计的有效性。
原文摘要 · Abstract (English)
Large Language Models (LLMs) increasingly exhibit \textbf{anthropomorphism} characteristics -- human-like qualities portrayed across their outlook, language, behavior, and reasoning functions. Such characteristics enable more intuitive and engaging human-AI interactions. However, current research on anthropomorphism remains predominantly risk-focused, emphasizing over-trust and user deception while offering limited design guidance. We argue that anthropomorphism should instead be treated as a \emph{concept of design} that can be intentionally tuned to support user goals. Drawing from multiple disciplines, we propose that the anthropomorphism of an LLM-based artifact should reflect the interaction between artifact designers and interpreters. This interaction is facilitated by cues embedded in the artifact by the designers and the (cognitive) responses of the interpreters to the cues. Cues are categorized into four dimensions: \textit{perceptive, linguistic, behavioral}, and \textit{cognitive}. By analyzing the manifestation and effectiveness of each cue, we provide a unified taxonomy with actionable levers for practitioners. Consequently, we advocate for function-oriented evaluations of anthropomorphic design.
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。