Aligning large language models (LLMs) behaviour with human intent is critical for future AI. An important yet often overlooked aspect of this alignment is the perceptual alignment. Perceptual modalities like touch are more multifaceted and nuanced compared to other sensory modalities such as vision. This work investigates how well LLMs align with human touch experiences using the "textile hand" task. We created a "Guess What Textile" interaction in which participants were given two textile samples -- a target and a reference -- to handle. Without seeing them, participants described the differences between them to the LLM. Using these descriptions, the LLM attempted to identify the target textile by assessing similarity within its high-dimensional embedding space. Our results suggest that a degree of perceptual alignment exists, however varies significantly among different textile samples. For example, LLM predictions are well aligned for silk satin, but not for cotton denim. Moreover, participants didn't perceive their textile experiences closely matched by the LLM predictions. This is only the first exploration into perceptual alignment around touch, exemplified through textile hand. We discuss possible sources of this alignment variance, and how better human-AI perceptual alignment can benefit future everyday tasks.

翻译：将大型语言模型（LLMs）的行为与人类意图对齐是未来人工智能发展的关键。其中，感知对齐作为重要却常被忽视的维度，相较于视觉等其他感官模态，触觉等感知模态更具多维性和细腻性。本研究通过"织物手感"任务探究LLMs与人类触觉体验的对齐程度。我们设计了"猜猜是什么织物"交互实验：参与者手持目标与参考两种织物样本，在无法看见的情况下向LLM描述两者差异，LLM则基于这些描述在其高维嵌入空间中评估相似性，进而识别目标织物。结果表明，感知对齐现象确实存在，但不同织物样本间差异显著——例如LLM对丝绸缎纹的预测对齐良好，而对棉质牛仔布的预测则偏差明显。此外，参与者感知其触觉体验与LLM预测的匹配度并未达到较高水平。作为以织物手感为范例的触觉感知对齐初步探索，本文讨论了感知对齐差异的可能成因，以及如何通过改善人机感知对齐赋能未来日常生活任务。