# SLIM-LLMs: Modeling of Style-Sensory Language RelationshipsThrough Low-Dimensional Representations

arXiv: https://arxiv.org/abs/2508.02901 · HTML: https://mlsanity.com/paper/2508.02901/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 35 references that are in the map.
- First posted on arXiv 4 Aug 2025.

## Builds on (most cited first, 8 of 8)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Spanish Pre-trained BERT Model and Evaluation Data](https://mlsanity.com/paper/2308.02976/) (2023)
- [Exploiting BERT for End-to-End Aspect-based Sentiment Analysis](https://mlsanity.com/paper/1910.00883/) (2019)
- [Ridge Regularization: an Essential Concept in Data Science](https://mlsanity.com/paper/2006.00371/) (2020)
- [Smells like Teen Spirit: An Exploration of Sensorial Style in Literary Genres](https://mlsanity.com/paper/2209.12352/) (2022)
- [Emergent Properties of Finetuned Language Representation Models](https://mlsanity.com/paper/1910.10832/) (2019)

## Built on by (most cited first, 1 of 1)

- [Structured Style-Rewrite with Chain-of-Thought Planning for Low-Resource Character Dialogue](https://mlsanity.com/paper/2603.05933/) (2026)

## Abstract (arXiv)

Sensorial language -- the language connected to our senses including vision, sound, touch, taste, smell, and interoception, plays a fundamental role in how we communicate experiences and perceptions. We explore the relationship between sensorial language and traditional stylistic features, like those measured by LIWC, using a novel Reduced-Rank Ridge Regression (R4) approach. We demonstrate that low-dimensional latent representations of LIWC features r = 24 effectively capture stylistic information for sensorial language prediction compared to the full feature set (r = 74). We introduce Stylometrically Lean Interpretable Models (SLIM-LLMs), which model non-linear relationships between these style dimensions. Evaluated across five genres, SLIM-LLMs with low-rank LIWC features match the performance of full-scale language models while reducing parameters by up to 80%.