# What Makes Linguistic Representations Good Models of High-Level Visual Perception in the Human Brain?

arXiv: https://arxiv.org/abs/2607.16214 · HTML: https://mlsanity.com/paper/2607.16214/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 37 of its 100 references that are in the map.
- First posted on arXiv 22 May 2026.

## Builds on (most cited first, 30 of 37)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Do Vision Transformers See Like Convolutional Neural Networks?](https://mlsanity.com/paper/2108.08810/) (2021)
- [Object Hallucination in Image Captioning](https://mlsanity.com/paper/1809.02156/) (2018)
- [MTEB: Massive Text Embedding Benchmark](https://mlsanity.com/paper/2210.07316/) (2022)
- [Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs](https://mlsanity.com/paper/2503.01743/) (2025)
- [Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models](https://mlsanity.com/paper/2409.17146/) (2024)
- [Getting aligned on representational alignment](https://mlsanity.com/paper/2310.13018/) (2023)
- [MMTEB: Massive Multilingual Text Embedding Benchmark](https://mlsanity.com/paper/2502.13595/) (2025)
- [Ministral 3](https://mlsanity.com/paper/2601.08584/) (2026)
- [The geometry of hidden representations of large transformer models](https://mlsanity.com/paper/2302.00294/) (2023)
- [Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Brain's Ventral Visual Pathway](https://mlsanity.com/paper/1411.6422/) (2014)
- [Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning](https://mlsanity.com/paper/2110.01705/) (2021)
- [Emergence of a High-Dimensional Abstraction Phase in Language Transformers](https://mlsanity.com/paper/2405.15471/) (2024)
- [The neuroconnectionist research programme](https://mlsanity.com/paper/2209.03718/) (2022)
- [The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models](https://mlsanity.com/paper/2311.05928/) (2023)

## Abstract (arXiv)

Image descriptions represented with language models (LMs) predict human brain responses to naturalistic images in high-level visual regions, but the factors driving this predictivity remain unclear. To investigate this, we systematically studied how images are described and which language models are used to embed those descriptions. For a common set of images, we considered six caption types -- including human-annotated and multiple machine-generated captions -- differing along several dimensions. Each caption was represented with five LMs, spanning autoregressive LMs trained to predict upcoming words and text embedders, i.e., LMs fine-tuned on semantic tasks requiring sentence/document-level representations. Machine-generated captions yielded significant brain predictivity and alignment, often surpassing human-annotated captions used in previous work. Across caption types, text embedders consistently outperformed autoregressive LMs, a pattern replicated when measuring behavioural alignment with image-similarity judgments. Analyses of caption representations from different model layers further revealed that both brain predictivity and behavioural alignment peak at intermediate network depth, shortly after a point thought to mark the emergence of syntactic and semantic structure. Altogether, our results demonstrate that both the content of image captions and the LM used to represent them influence brain- and behaviour-modelling performance, establishing caption embeddings as a useful tool for studying high-level visual perception.