# Probing the Emergence of Cross-lingual Alignment during LLM Training

arXiv: https://arxiv.org/abs/2406.13229 · HTML: https://mlsanity.com/paper/2406.13229/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 40 references that are in the map.
- First posted on arXiv 19 Jun 2024.

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

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [XNLI: Evaluating Cross-lingual Sentence Representations](https://mlsanity.com/paper/1809.05053/) (2018)
- [XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization](https://mlsanity.com/paper/2003.11080/) (2020)
- [How multilingual is Multilingual BERT?](https://mlsanity.com/paper/1906.01502/) (2019)
- [On the Cross-lingual Transferability of Monolingual Representations](https://mlsanity.com/paper/1910.11856/) (2019)
- [Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT](https://mlsanity.com/paper/1904.09077/) (2019)
- [Few-shot Learning with Multilingual Language Models](https://mlsanity.com/paper/2112.10668/) (2021)
- [Are All Languages Created Equal in Multilingual BERT?](https://mlsanity.com/paper/2005.09093/) (2020)
- [Emerging Cross-lingual Structure in Pretrained Language Models](https://mlsanity.com/paper/1911.01464/) (2019)
- [Probing Pretrained Language Models for Lexical Semantics](https://mlsanity.com/paper/2010.05731/) (2020)
- [The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset](https://mlsanity.com/paper/2303.03915/) (2023)
- [Composable Sparse Fine-Tuning for Cross-Lingual Transfer](https://mlsanity.com/paper/2110.07560/) (2021)
- [Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs](https://mlsanity.com/paper/2309.07311/) (2023)
- [Multilingual Alignment of Contextual Word Representations](https://mlsanity.com/paper/2002.03518/) (2020)
- [Training Trajectories of Language Models Across Scales](https://mlsanity.com/paper/2212.09803/) (2022)
- [Probing Across Time: What Does RoBERTa Know and When?](https://mlsanity.com/paper/2104.07885/) (2021)
- [Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing](https://mlsanity.com/paper/1902.09492/) (2019)
- [First Align, then Predict: Understanding the Cross-Lingual Ability of Multilingual BERT](https://mlsanity.com/paper/2101.11109/) (2021)
- [How Language-Neutral is Multilingual BERT?](https://mlsanity.com/paper/1911.03310/) (2019)
- [Intrinsic Probing through Dimension Selection](https://mlsanity.com/paper/2010.02812/) (2020)
- [UniMorph 2.0: Universal Morphology](https://mlsanity.com/paper/1810.11101/) (2018)
- [Deep Subjecthood: Higher-Order Grammatical Features in Multilingual BERT](https://mlsanity.com/paper/2101.11043/) (2021)
- [Analyzing the Mono- and Cross-Lingual Pretraining Dynamics of Multilingual Language Models](https://mlsanity.com/paper/2205.11758/) (2022)
- [Discovering Language-neutral Sub-networks in Multilingual Language Models](https://mlsanity.com/paper/2205.12672/) (2022)
- [Marrying Universal Dependencies and Universal Morphology](https://mlsanity.com/paper/1810.06743/) (2018)
- [Shaking Syntactic Trees on the Sesame Street: Multilingual Probing with Controllable Perturbations](https://mlsanity.com/paper/2109.14017/) (2021)

## Built on by (most cited first, 30 of 39)

- [Middle-Layer Representation Alignment for Cross-Lingual Transfer in Fine-Tuned LLMs](https://mlsanity.com/paper/2502.14830/) (2025)
- [Representation Engineering for Large-Language Models: Survey and Research Challenges](https://mlsanity.com/paper/2502.17601/) (2025)
- [Multilingual Large Language Models: A Systematic Survey](https://mlsanity.com/paper/2411.11072/) (2024)
- [Cross-lingual Transfer of Reward Models in Multilingual Alignment](https://mlsanity.com/paper/2410.18027/) (2024)
- [LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through Probing](https://mlsanity.com/paper/2505.16491/) (2025)
- [Multi-OphthaLingua: A Multilingual Benchmark for Assessing and Debiasing LLM Ophthalmological QA in LMICs](https://mlsanity.com/paper/2412.14304/) (2024)
- [Tracing Multilingual Factual Knowledge Acquisition in Pretraining](https://mlsanity.com/paper/2505.14824/) (2025)
- [From Neurons to Semantics: Evaluating Cross-Linguistic Alignment Capabilities of Large Language Models via Neurons Alignment](https://mlsanity.com/paper/2507.14900/) (2025)
- [On the Limitations of Language Targeted Pruning: Investigating the Calibration Language Impact in Multilingual LLM Pruning](https://mlsanity.com/paper/2408.14398/) (2024)
- [Are Knowledge and Reference in Multilingual Language Models Cross-Lingually Consistent?](https://mlsanity.com/paper/2507.12838/) (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)
- [ATACompressor: Adaptive Task-Aware Compression for Efficient Long-Context Processing in LLMs](https://mlsanity.com/paper/2602.03226/) (2026)
- [CoCo-CoLa: Evaluating and Improving Language Adherence in Multilingual LLMs](https://mlsanity.com/paper/2502.12476/) (2025)
- [Enhancing LLM Language Adaption through Cross-lingual In-Context Pre-training](https://mlsanity.com/paper/2504.20484/) (2025)
- [Scale Dependent Data Duplication](https://mlsanity.com/paper/2603.06603/) (2026)
- [Multilingual LLMs Struggle to Link Orthography and Semantics in Bilingual Word Processing](https://mlsanity.com/paper/2501.09127/) (2025)
- [When Language Shapes Thought: Cross-Lingual Transfer of Factual Knowledge in Question Answering](https://mlsanity.com/paper/2505.24409/) (2025)
- [Can Embedding Similarity Predict Cross-Lingual Transfer? A Systematic Study on African Languages](https://mlsanity.com/paper/2601.03168/) (2026)
- [Do Prompts Reshape Representations? An Empirical Study of Prompting Effects on Embeddings](https://mlsanity.com/paper/2510.19694/) (2025)
- [CrossHallu: Do Hallucination Signals Generalize Across Languages and Domains in Large Language Model's Internals?](https://mlsanity.com/paper/2607.04029/) (2026)
- [Uncovering Hidden Violent Tendencies in LLMs: A Demographic Analysis via Behavioral Vignettes](https://mlsanity.com/paper/2506.20822/) (2025)
- [From Monolingual to Bilingual: Investigating Language Conditioning in Large Language Models for Psycholinguistic Tasks](https://mlsanity.com/paper/2508.02502/) (2025)
- [A Review of Developmental Interpretability in Large Language Models](https://mlsanity.com/paper/2508.15841/) (2025)
- [Learning to Look at the Other Side: A Semantic Probing Study of Word Embeddings in LLMs with Enabled Bidirectional Attention](https://mlsanity.com/paper/2510.01652/) (2025)
- [LuxInstruct: A Cross-Lingual Instruction Tuning Dataset For Luxembourgish](https://mlsanity.com/paper/2510.07074/) (2025)
- [Cross-Lingual Steering for Figurative Language Generation](https://mlsanity.com/paper/2605.30443/) (2026)
- [Shared Doubt: Zero-Shot Cross-Lingual Confidence Estimation for Language Models](https://mlsanity.com/paper/2605.31220/) (2026)
- [EnSiTa - A Trilingual Multi-Domain Parallel Dataset and Benchmark for Domain-Specific Machine Translation](https://mlsanity.com/paper/2609.29511/) (2026)
- [Can linguists better understand DNA?](https://mlsanity.com/paper/2412.07678/) (2024)
- [Domain Pre-training Impact on Representations](https://mlsanity.com/paper/2505.24455/) (2025)

## Abstract (arXiv)

Multilingual Large Language Models (LLMs) achieve remarkable levels of zero-shot cross-lingual transfer performance. We speculate that this is predicated on their ability to align languages without explicit supervision from parallel sentences. While representations of translationally equivalent sentences in different languages are known to be similar after convergence, however, it remains unclear how such cross-lingual alignment emerges during pre-training of LLMs. Our study leverages intrinsic probing techniques, which identify which subsets of neurons encode linguistic features, to correlate the degree of cross-lingual neuron overlap with the zero-shot cross-lingual transfer performance for a given model. In particular, we rely on checkpoints of BLOOM, a multilingual autoregressive LLM, across different training steps and model scales. We observe a high correlation between neuron overlap and downstream performance, which supports our hypothesis on the conditions leading to effective cross-lingual transfer. Interestingly, we also detect a degradation of both implicit alignment and multilingual abilities in certain phases of the pre-training process, providing new insights into the multilingual pretraining dynamics.