arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.18510cs.AI
收藏

改进AI与人类的情感对齐:人类对Stable Diffusion v1、DALL-E 2和DALL-E 3所表达情感的评分

Improved Emotional Alignment of AI and Humans: Human Ratings of Emotions Expressed by Stable Diffusion v1, DALL-E 2, and DALL-E 3

Delft University of Technology(代尔夫特理工大学);Delft Institute of Positive Design(代尔夫特积极设计研究所);Department of Human-Centered Design(以人为本设计系);Playpower Labs Pvt Ltd(Playpower实验室私人有限公司);School of Design(设计学院);Hong Kong Polytechnic University(香港理工大学);Department of Psychology(心理学系);Utrecht University(乌得勒支大学)

James Derek Lomas, Willem van der Maden, Sohhom Bandyopadhyay, Giovanni Lion, Nirmal Patel, Gyanesh Jain, Yanna Litowsky, Haian Xue, Pieter Desmet

AI总结:

本研究通过调查评估DALL-E 2、DALL-E 3和Stable Diffusion v1生成图像的情感表达与人类感知的对齐程度,发现模型能良好表达情感,但对齐度依赖模型和具体情感,为未来心理健康AI提供改进方向。

摘要:

生成式AI系统越来越能够通过文本和图像表达情感。有效的情感表达可能在AI系统的效能中发挥重要作用——尤其是那些旨在支持人类心理健康和福祉的系统。这促使我们开展当前研究,以更好地理解AI表达的情感与人类对情感的感知之间的对齐。当AI试图表达特定情感时,我们如何评估它们是否成功?为了回答这个问题,我们设计了一项调查,以衡量生成式AI表达的情感与人类感知之间的对齐程度。我们使用了三个生成式图像模型(DALL-E 2、DALL-E 3和Stable Diffusion v1)生成了240个图像示例,每个示例都基于一个旨在表达五种积极和五种消极情感的提示词,这些情感同时涉及人类和机器人。我们从Prolific网站招募了24名参与者,他们对AI生成的情感表达与用于生成该情感的文本提示(例如,“一个表达娱乐情感的机器人”)之间的对齐程度进行了评分。我们的评估结果表明,生成式AI模型确实能够产生与一系列人类情感良好对齐的情感表达;然而,我们表明这种对齐在很大程度上取决于所使用的AI模型以及情感本身。我们分析了这些系统性能的差异,以识别未来改进的差距。最后,我们讨论了这对未来旨在支持心理健康和福祉的AI系统的启示。

英文摘要:

Generative AI systems are increasingly capable of expressing emotions via text and imagery. Effective emotional expression will likely play a major role in the efficacy of AI systems -- particularly those designed to support human mental health and wellbeing. This motivates our present research to better understand the alignment of AI expressed emotions with the human perception of emotions. When AI tries to express a particular emotion, how might we assess whether they are successful? To answer this question, we designed a survey to measure the alignment between emotions expressed by generative AI and human perceptions. Three generative image models (DALL-E 2, DALL-E 3 and Stable Diffusion v1) were used to generate 240 examples of images, each of which was based on a prompt designed to express five positive and five negative emotions across both humans and robots. 24 participants recruited from the Prolific website rated the alignment of AI-generated emotional expressions with a text prompt used to generate the emotion (i.e., "A robot expressing the emotion amusement"). The results of our evaluation suggest that generative AI models are indeed capable of producing emotional expressions that are well-aligned with a range of human emotions; however, we show that the alignment significantly depends upon the AI model used and the emotion itself. We analyze variations in the performance of these systems to identify gaps for future improvement. We conclude with a discussion of the implications for future AI systems designed to support mental health and wellbeing.

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。

↑