嗅探AI:我的“辣”是你的“辣”吗?探索大语言模型与人类嗅觉体验的感知对齐
Sniff AI: Is My 'Spicy' Your 'Spicy'? Exploring LLM's Perceptual Alignment with Human Smell Experiences
AI总结:
本研究通过用户研究评估大语言模型对气味描述的感知对齐,发现其存在偏见且识别有限,并探讨了多感官体验整合的局限与机遇。
摘要:
将人工智能与人类意图对齐非常重要,然而感知对齐——即AI如何解读我们所看、所听或所闻——仍未得到充分探索。本研究聚焦于嗅觉,即人类的嗅觉体验。我们开展了一项包含40名参与者的用户研究,以探究AI在多大程度上能够解读人类对气味的描述。参与者执行了“嗅闻并描述”的交互任务,我们设计的AI系统根据参与者的描述尝试猜测他们正在体验的气味。这些任务评估了大语言模型(LLM)的上下文理解能力,以及其内部状态(高维嵌入空间)中气味关系的表征。我们采用定量和定性两种方法来评估AI系统的性能。结果表明,感知对齐程度有限,系统对某些气味(如柠檬和薄荷)存在偏见,而持续无法识别其他气味(如迷迭香)。我们结合人机对齐的进展讨论了这些发现,强调了将多感官体验整合到人机交互系统中的局限性和机遇。
英文摘要:
Aligning AI with human intent is important, yet perceptual alignment-how AI interprets what we see, hear, or smell-remains underexplored. This work focuses on olfaction, human smell experiences. We conducted a user study with 40 participants to investigate how well AI can interpret human descriptions of scents. Participants performed "sniff and describe" interactive tasks, with our designed AI system attempting to guess what scent the participants were experiencing based on their descriptions. These tasks evaluated the Large Language Model's (LLMs) contextual understanding and representation of scent relationships within its internal states - high-dimensional embedding space. Both quantitative and qualitative methods were used to evaluate the AI system's performance. Results indicated limited perceptual alignment, with biases towards certain scents, like lemon and peppermint, and continued failing to identify others, like rosemary. We discuss these findings in light of human-AI alignment advancements, highlighting the limitations and opportunities for enhancing HCI systems with multisensory experience integration.
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。