# Converging to a Lingua Franca: Evolution of Linguistic Regions and Semantics Alignment in Multilingual Large Language Models

arXiv: https://arxiv.org/abs/2410.11718 · HTML: https://mlsanity.com/paper/2410.11718/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 41 references that are in the map.
- First posted on arXiv 15 Oct 2024.

## Builds on (most cited first, 19 of 19)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [How multilingual is Multilingual BERT?](https://mlsanity.com/paper/1906.01502/) (2019)
- [XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages](https://mlsanity.com/paper/2106.13822/) (2021)
- [Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca](https://mlsanity.com/paper/2304.08177/) (2023)
- [Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT](https://mlsanity.com/paper/1904.09077/) (2019)
- [Do Llamas Work in English? On the Latent Language of Multilingual Transformers](https://mlsanity.com/paper/2402.10588/) (2024)
- [SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF](https://mlsanity.com/paper/2310.05344/) (2023)
- [Cross-lingual Prompting: Improving Zero-shot Chain-of-Thought Reasoning across Languages](https://mlsanity.com/paper/2310.14799/) (2023)
- [Language Contamination Helps Explain the Cross-lingual Capabilities of English Pretrained Models](https://mlsanity.com/paper/2204.08110/) (2022)
- [On the Language Neutrality of Pre-trained Multilingual Representations](https://mlsanity.com/paper/2004.05160/) (2020)
- [Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM's Translation Capability](https://mlsanity.com/paper/2305.10266/) (2023)
- [TIM: Teaching Large Language Models to Translate with Comparison](https://mlsanity.com/paper/2307.04408/) (2023)
- [LINGUIST: Language Model Instruction Tuning to Generate Annotated Utterances for Intent Classification and Slot Tagging](https://mlsanity.com/paper/2209.09900/) (2022)
- [Multilingual Brain Surgeon: Large Language Models Can be Compressed Leaving No Language Behind](https://mlsanity.com/paper/2404.04748/) (2024)
- [A Simple and Effective Method to Improve Zero-Shot Cross-Lingual Transfer Learning](https://mlsanity.com/paper/2210.09934/) (2022)

## Built on by (most cited first, 23 of 23)

- [The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities](https://mlsanity.com/paper/2411.04986/) (2024)
- [Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers](https://mlsanity.com/paper/2411.08745/) (2024)
- [Aligning LLMs for Multilingual Consistency in Enterprise Applications](https://mlsanity.com/paper/2509.23659/) (2025)
- [Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings](https://mlsanity.com/paper/2505.24341/) (2025)
- [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)
- [From Neurons to Semantics: Evaluating Cross-Linguistic Alignment Capabilities of Large Language Models via Neurons Alignment](https://mlsanity.com/paper/2507.14900/) (2025)
- [How Syntax Specialization Emerges in Language Models](https://mlsanity.com/paper/2505.19548/) (2025)
- [A Review of Incorporating Psychological Theories in LLMs](https://mlsanity.com/paper/2505.00003/) (2025)
- [How a Bilingual LM Becomes Bilingual: Tracing Internal Representations with Sparse Autoencoders](https://mlsanity.com/paper/2503.06394/) (2025)
- [When Meanings Meet: Investigating the Emergence and Quality of Shared Concept Spaces during Multilingual Language Model Training](https://mlsanity.com/paper/2601.22851/) (2026)
- [Beyond the Rosetta Stone: Unification Forces in Generalization Dynamics](https://mlsanity.com/paper/2508.11017/) (2025)
- [High-Dimensional Interlingual Representations of Large Language Models](https://mlsanity.com/paper/2503.11280/) (2025)
- [XToM: Exploring the Multilingual Theory of Mind for Large Language Models](https://mlsanity.com/paper/2506.02461/) (2025)
- [Layer-Targeted Multilingual Knowledge Erasure in Large Language Models](https://mlsanity.com/paper/2602.22562/) (2026)
- [Uncovering Cross-Linguistic Disparities in LLMs using Sparse Autoencoders](https://mlsanity.com/paper/2507.18918/) (2025)
- [Copy First, Translate Later: Interpreting Translation Dynamics in Multilingual Pretraining](https://mlsanity.com/paper/2604.17633/) (2026)
- [Shared Doubt: Zero-Shot Cross-Lingual Confidence Estimation for Language Models](https://mlsanity.com/paper/2605.31220/) (2026)
- [Polysemy of Synthetic Neurons Towards a New Type of Explanatory Categorical Vector Spaces](https://mlsanity.com/paper/2505.07831/) (2025)
- [Advancing Uto-Aztecan Language Technologies: A Case Study on the Endangered Comanche Language](https://mlsanity.com/paper/2505.18159/) (2025)
- [Why Vision Fails as a Universal Bridge: Rectifying Modality Asynchrony in Multilingual MLLMs](https://mlsanity.com/paper/2608.15085/) (2026)
- [Cross-lingual Functional Vectors for Emotion Detection in Large Language Models](https://mlsanity.com/paper/2608.29613/) (2026)
- [μ2-Bench: A Multilingual Machine Unlearning Benchmark](https://mlsanity.com/paper/2609.20945/) (2026)
- [Linguistic Loopholes in LLM Unlearning: From a 174-Language Benchmark to Coverage-Aware Unlearning](https://mlsanity.com/paper/2609.40286/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated remarkable performance, particularly in multilingual contexts. While recent studies suggest that LLMs can transfer skills learned in one language to others, the internal mechanisms behind this ability remain unclear. We observed that the neuron activation patterns of LLMs exhibit similarities when processing the same language, revealing the existence and location of key linguistic regions. Additionally, we found that neuron activation patterns are similar when processing sentences with the same semantic meaning in different languages. This indicates that LLMs map semantically identical inputs from different languages into a "Lingua Franca", a common semantic latent space that allows for consistent processing across languages. This semantic alignment becomes more pronounced with training and increased model size, resulting in a more language-agnostic activation pattern. Moreover, we found that key linguistic neurons are concentrated in the first and last layers of LLMs, becoming denser in the first layers as training progresses. Experiments on BLOOM and LLaMA2 support these findings, highlighting the structural evolution of multilingual LLMs during training and scaling up. This paper provides insights into the internal workings of LLMs, offering a foundation for future improvements in their cross-lingual capabilities.