arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2502.14229cs.HC
收藏

生成式人工智能中的前馈:设计空间的机遇

Feedforward in Generative AI: Opportunities for a Design Space

Bryan Min, Haijun Xia

AI总结:

针对用户难以预测生成式AI(GenAI)输出、需反复交互导致认知负荷高的问题,提出需设计兼具信息性反馈与前馈(提示提交前告知AI将生成内容)的GenAI系统,并通过四类应用实例探讨前馈设计空间与指南,以释放GenAI潜力。

摘要:

生成式人工智能(GenAI)模型在不同场景下增强生产力和认知能力的能力空前强大。然而,用户难以预测AI将生成什么内容仍是一个根本性挑战。因此,他们必须与AI的反馈进行过多的交互以明确自身意图,导致认知负荷显著增加和时间投入过多。我们的目标是提出这样一种观点:为了让用户在各种场景下无缝利用GenAI系统的全部潜力,我们必须设计不仅能提供信息性反馈,还能提供信息性前馈的GenAI系统——即能在用户提交提示前告知其AI将生成什么内容的设计。为了引发关于GenAI中前馈的讨论,我们针对四种GenAI应用设计了多样化的前馈实例:对话式UI、文档编辑器、可塑界面和自动化智能体,并探讨了这些设计如何助力更严谨地研究前馈的设计空间,以及为所有GenAI系统的前馈制定一套指南。

英文摘要:

Generative AI (GenAI) models have become more capable than ever at augmenting productivity and cognition across diverse contexts. However, a fundamental challenge remains as users struggle to anticipate what AI will generate. As a result, they must engage in excessive turn-taking with the AI's feedback to clarify their intent, leading to significant cognitive load and time investment. Our goal is to advance the perspective that in order for users to seamlessly leverage the full potential of GenAI systems across various contexts, we must design GenAI systems that not only provide informative feedback but also informative feedforward -- designs that tell users what AI will generate before the user submits their prompt. To spark discussion on feedforward in GenAI, we designed diverse instantiations of feedforward across four GenAI applications: conversational UIs, document editors, malleable interfaces, and automation agents, and discussed how these designs can contribute to a more rigorous investigation of a design space and a set of guidelines for feedforward in all GenAI systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑