Who Controls the Conversation? User Perspectives On Generative AI (LLM) System Prompts

要旨

System prompts---instructions that shape the behaviour of generative AI systems---strongly influence system outputs and users' experiences. They define the model's guidelines, `personality', and guardrails, taking precedence over user inputs. Despite their influence, transparency is limited: system prompts are generally not made public and most platforms instruct models to conceal them, leaving users disconnected from and unaware of a key mechanism guiding and governing their AI interactions. This paper argues that system prompts warrant explicit, user-centred design attention and, focusing on large language models (LLMs), asks: what do system prompts contain, how do end-users perceive them, and what do these perceptions offer for design and governance practice? Our results reveal user perspectives on: the benefits and risks of system prompts; the values they prefer to be associated with prompt-design; their levels of comfort with different types of prompts; and degrees of transparency and user control regarding prompt content. From these findings emerge considerations for how designers can better align system prompt mechanisms with user expectations and preferences over these mechanisms that directly shape how generative AI systems behave.

受賞
Best Paper
著者
Anna Neumann
University Duisburg-Essen, Duisburg, Germany
Yulu Pi
University Duisburg-Essen, Duisburg, Germany
Jatinder Singh
University Duisburg-Essen, Duisburg, Germany

会議: CHI 2026

ACM CHI Conference on Human Factors in Computing Systems

セッション: Conversational AI, Agency and Control

P1 - Room 118
7 件の発表
2026-04-15 18:00:00
2026-04-15 19:30:00