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

arXiv: https://arxiv.org/abs/2603.03313 · HTML: https://mlsanity.com/paper/2603.03313/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 11 references that are in the map.
- First posted on arXiv 9 Feb 2026.

## Builds on (most cited first, 2 of 2)

- [Psycholinguistic Word Features: a New Approach for the Evaluation of LLMs Alignment with Humans](https://mlsanity.com/paper/2506.22439/) (2025)
- [Does Visual Grounding Enhance the Understanding of Embodied Knowledge in Large Language Models?](https://mlsanity.com/paper/2510.16924/) (2025)

## Abstract (arXiv)

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.