# When Meanings Meet: Investigating the Emergence and Quality of Shared Concept Spaces during Multilingual Language Model Training

arXiv: https://arxiv.org/abs/2601.22851 · HTML: https://mlsanity.com/paper/2601.22851/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 45 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## Builds on (most cited first, 28 of 28)

- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research](https://mlsanity.com/paper/2402.00159/) (2024)
- [Do Llamas Work in English? On the Latent Language of Multilingual Transformers](https://mlsanity.com/paper/2402.10588/) (2024)
- [Learning Word Vectors for 157 Languages](https://mlsanity.com/paper/1802.06893/) (2018)
- [How to use and interpret activation patching](https://mlsanity.com/paper/2404.15255/) (2024)
- [EuroLLM: Multilingual Language Models for Europe](https://mlsanity.com/paper/2409.16235/) (2024)
- [Language Contamination Helps Explain the Cross-lingual Capabilities of English Pretrained Models](https://mlsanity.com/paper/2204.08110/) (2022)
- [On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons](https://mlsanity.com/paper/2404.02431/) (2024)
- [Do Multilingual LLMs Think In English?](https://mlsanity.com/paper/2502.15603/) (2025)
- [Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neurons](https://mlsanity.com/paper/2308.13198/) (2023)
- [Some Languages are More Equal than Others: Probing Deeper into the Linguistic Disparity in the NLP World](https://mlsanity.com/paper/2210.08523/) (2022)
- [Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers](https://mlsanity.com/paper/2411.08745/) (2024)
- [Probing the Emergence of Cross-lingual Alignment during LLM Training](https://mlsanity.com/paper/2406.13229/) (2024)
- [Multi-SimLex: A Large-Scale Evaluation of Multilingual and Cross-Lingual Lexical Semantic Similarity](https://mlsanity.com/paper/2003.04866/) (2020)
- [Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs](https://mlsanity.com/paper/2406.09265/) (2024)
- [The Dual-Route Model of Induction](https://mlsanity.com/paper/2504.03022/) (2025)
- [Converging to a Lingua Franca: Evolution of Linguistic Regions and Semantics Alignment in Multilingual Large Language Models](https://mlsanity.com/paper/2410.11718/) (2024)
- [PreAlign: Boosting Cross-Lingual Transfer by Early Establishment of Multilingual Alignment](https://mlsanity.com/paper/2407.16222/) (2024)
- [Concept Space Alignment in Multilingual LLMs](https://mlsanity.com/paper/2410.01079/) (2024)
- [The Multilingual Divide and Its Impact on Global AI Safety](https://mlsanity.com/paper/2505.21344/) (2025)
- [How Does Alignment Enhance LLMs' Multilingual Capabilities? A Language Neurons Perspective](https://mlsanity.com/paper/2505.21505/) (2025)
- [The Transfer Neurons Hypothesis: An Underlying Mechanism for Language Latent Space Transitions in Multilingual LLMs](https://mlsanity.com/paper/2509.17030/) (2025)
- [From Unaligned to Aligned: Scaling Multilingual LLMs with Multi-Way Parallel Corpora](https://mlsanity.com/paper/2505.14045/) (2025)
- [Cross-Lingual Generalization and Compression: From Language-Specific to Shared Neurons](https://mlsanity.com/paper/2506.01629/) (2025)
- [Responsible Multilingual Large Language Models: A Survey of Development, Applications, and Societal Impact](https://mlsanity.com/paper/2410.17532/) (2024)
- [Controlling Language Confusion in Multilingual LLMs](https://mlsanity.com/paper/2505.19116/) (2025)

## Built on by (most cited first, 5 of 5)

- [Copy First, Translate Later: Interpreting Translation Dynamics in Multilingual Pretraining](https://mlsanity.com/paper/2604.17633/) (2026)
- [Mimir: Large-scale Multilingual Concept Modeling](https://mlsanity.com/paper/2605.25263/) (2026)
- [What, Where, and How: Disentangling the Roles of Task, Language, and Model in Code Model Representations](https://mlsanity.com/paper/2607.21491/) (2026)
- [Cross-Lingual Alignment Without Joint Training: Do Monolingual Language Models Converge on Universal Representations?](https://mlsanity.com/paper/2608.27115/) (2026)
- [Beetle: A Bilingual Model Suite for Modelling Second-Language Processing](https://mlsanity.com/paper/2609.22633/) (2026)

## Abstract (arXiv)

Training Large Language Models (LLMs) with high multilingual coverage is becoming increasingly important -- especially when monolingual resources are scarce. Recent studies have found that LLMs process multilingual inputs in shared concept spaces, thought to support generalization and cross-lingual transfer. However, these prior studies often do not use causal methods, lack deeper error analysis or focus on the final model only, leaving open how these spaces emerge during training. We investigate the development of language-agnostic concept spaces during pretraining of EuroLLM through the causal interpretability method of activation patching. We isolate cross-lingual concept representations, then inject them into a translation prompt to investigate how consistently translations can be altered, independently of the language. We find that shared concept spaces emerge early} and continue to refine, but that alignment with them is language-dependent}. Furthermore, in contrast to prior work, our fine-grained manual analysis reveals that some apparent gains in translation quality reflect shifts in behavior -- like selecting senses for polysemous words or translating instead of copying cross-lingual homographs -- rather than improved translation ability. Our findings offer new insight into the training dynamics of cross-lingual alignment and the conditions under which causal interpretability methods offer meaningful insights in multilingual contexts.