# From Words to Waves: Analyzing Concept Formation in Speech and Text-Based Foundation Models

arXiv: https://arxiv.org/abs/2506.01133 · HTML: https://mlsanity.com/paper/2506.01133/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 32 of its 40 references that are in the map.
- First posted on arXiv 1 Jun 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 30 of 32)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [Qwen2-Audio Technical Report](https://mlsanity.com/paper/2407.10759/) (2024)
- [SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing](https://mlsanity.com/paper/2110.07205/) (2021)
- [SeamlessM4T: Massively Multilingual & Multimodal Machine Translation](https://mlsanity.com/paper/2308.11596/) (2023)
- [What Happens To BERT Embeddings During Fine-tuning?](https://mlsanity.com/paper/2004.14448/) (2020)
- [ChatGPT Makes Medicine Easy to Swallow: An Exploratory Case Study on Simplified Radiology Reports](https://mlsanity.com/paper/2212.14882/) (2022)
- [SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech](https://mlsanity.com/paper/2111.10367/) (2021)
- [Self-Supervised Speech Representations are More Phonetic than Semantic](https://mlsanity.com/paper/2406.08619/) (2024)
- [What Do Self-Supervised Speech Models Know About Words?](https://mlsanity.com/paper/2307.00162/) (2023)
- [HumanOmni: A Large Vision-Speech Language Model for Human-Centric Video Understanding](https://mlsanity.com/paper/2501.15111/) (2025)
- [Discovering Latent Concepts Learned in BERT](https://mlsanity.com/paper/2205.07237/) (2022)
- [The Parallel Meaning Bank: Towards a Multilingual Corpus of Translations Annotated with Compositional Meaning Representations](https://mlsanity.com/paper/1702.03964/) (2017)
- [Analyzing Encoded Concepts in Transformer Language Models](https://mlsanity.com/paper/2206.13289/) (2022)
- [Probing self-supervised speech models for phonetic and phonemic information: a case study in aspiration](https://mlsanity.com/paper/2306.06232/) (2023)
- [Asking without Telling: Exploring Latent Ontologies in Contextual Representations](https://mlsanity.com/paper/2004.14513/) (2020)
- [How transfer learning impacts linguistic knowledge in deep NLP models?](https://mlsanity.com/paper/2105.15179/) (2021)
- [On the Transformation of Latent Space in Fine-Tuned NLP Models](https://mlsanity.com/paper/2210.12696/) (2022)
- [Human-like Linguistic Biases in Neural Speech Models: Phonetic Categorization and Phonotactic Constraints in Wav2Vec2.0](https://mlsanity.com/paper/2407.03005/) (2024)
- [Can LLMs facilitate interpretation of pre-trained language models?](https://mlsanity.com/paper/2305.13386/) (2023)
- [SD-HuBERT: Sentence-Level Self-Distillation Induces Syllabic Organization in HuBERT](https://mlsanity.com/paper/2310.10803/) (2023)
- [NeuroX Library for Neuron Analysis of Deep NLP Models](https://mlsanity.com/paper/2305.17073/) (2023)
- [What do End-to-End Speech Models Learn about Speaker, Language and Channel Information? A Layer-wise and Neuron-level Analysis](https://mlsanity.com/paper/2107.00439/) (2021)
- [Scaling up Discovery of Latent Concepts in Deep NLP Models](https://mlsanity.com/paper/2308.10263/) (2023)
- [How do Multimodal Foundation Models Encode Text and Speech? An Analysis of Cross-Lingual and Cross-Modal Representations](https://mlsanity.com/paper/2411.17666/) (2024)
- [What Do Speech Foundation Models Not Learn About Speech?](https://mlsanity.com/paper/2410.12948/) (2024)

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

- [The Curious Case of Visual Grounding: Different Effects for Speech- and Text-based Language Encoders](https://mlsanity.com/paper/2509.15837/) (2025)

## Abstract (arXiv)

The emergence of large language models (LLMs) has demonstrated that systems trained solely on text can acquire extensive world knowledge, develop reasoning capabilities, and internalize abstract semantic concepts--showcasing properties that can be associated with general intelligence. This raises an intriguing question: Do such concepts emerge in models trained on other modalities, such as speech? Furthermore, when models are trained jointly on multiple modalities: Do they develop a richer, more structured semantic understanding? To explore this, we analyze the conceptual structures learned by speech and textual models both individually and jointly. We employ Latent Concept Analysis, an unsupervised method for uncovering and interpreting latent representations in neural networks, to examine how semantic abstractions form across modalities. For reproducibility we made scripts and other resources available to the community.