arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.03313cs.CLcs.AI
收藏

微调如何改善大语言模型中的感知运动表征

How does fine-tuning improve sensorimotor representations in large language models?

Department of Experimental Psychology, Ghent University(实验心理学系,根特大学);Information Processing and Telecommunications Center (IPTC), Universidad Politécnica de Madrid, Spain(信息处理与电信中心(IPTC),马德里理工大学,西班牙)

Minghua Wu, Javier Conde, Pedro Reviriego, Marc Brysbaert

AI总结:

本研究通过微调改善大语言模型的感知运动表征,发现其在语言和感知运动维度上具有良好的泛化能力,但对学习目标敏感,无法跨任务格式迁移。

摘要:

大型语言模型(LLMs)表现出显著的

英文摘要:

Large Language Models (LLMs) exhibit a significant "embodiment gap", where their text-based representations fail to align with human sensorimotor experiences. This study systematically investigates whether and how task-specific fine-tuning can bridge this gap. Utilizing Representational Similarity Analysis (RSA) and dimension-specific correlation metrics, we demonstrate that the internal representations of LLMs can be steered toward more embodied, grounded patterns through fine-tuning. Furthermore, the results show that while sensorimotor improvements generalize robustly across languages and related sensory-motor dimensions, they are highly sensitive to the learning objective, failing to transfer across two disparate task formats.

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。

↑