用树的隐喻揭示大模型设计中的潜在假设与可能性
Ontologies in Design: How Imagining a Tree Reveals Possibilites and Assumptions in Large Language Models
- 以'树'为隐喻开展本体论分析，探索模型能思考什么
- 发现不同提示下四款聊天机器人展现截然不同的认知可能
- 适合关注AI伦理、系统设计的学者与实践者阅读
随着生成式AI的普及，社会技术学者和批评者已识别出诸多潜在危害，现有分析多聚焦于价值与伦理（如偏见）。我们提出，本体论——即允许我们思考或谈论什么——是分析这些系统中一个关键却未被充分重视的维度。为此，我们提出四种设计本体论的实践导向：多元性、扎根性、生机性与实施性。通过两项本体论分析验证：一是考察四款基于LLM的聊天机器人在提示任务中的回应；二是分析一个基于LLM的智能体模拟架构。研究揭示了在大模型开发全链条中，本体论视角如何打开新的可能性，并讨论其在社会技术系统设计中的机遇与局限。
原文摘要 · Abstract (English)
Amid the recent uptake of Generative AI, sociotechnical scholars and critics have traced a multitude of resulting harms, with analyses largely focused on values and axiology (e.g., bias). While value-based analyses are crucial, we argue that ontologies -- concerning what we allow ourselves to think or talk about -- is a vital but under-recognized dimension in analyzing these systems. Proposing a need for a practice-based engagement with ontologies, we offer four orientations for considering ontologies in design: pluralism, groundedness, liveliness, and enactment. We share examples of potentialities that are opened up through these orientations across the entire LLM development pipeline by conducting two ontological analyses: examining the responses of four LLM-based chatbots in a prompting exercise, and analyzing the architecture of an LLM-based agent simulation. We conclude by sharing opportunities and limitations of working with ontologies in the design and development of sociotechnical systems.
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。