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.
@article{arxiv.2603.03313,
title = {How does fine-tuning improve sensorimotor representations in large language models?},
author = {Minghua Wu and Javier Conde and Pedro Reviriego and Marc Brysbaert},
journal= {arXiv preprint arXiv:2603.03313},
year = {2026}
}