# Copy First, Translate Later: Interpreting Translation Dynamics in Multilingual Pretraining

arXiv: https://arxiv.org/abs/2604.17633 · HTML: https://mlsanity.com/paper/2604.17633/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 51 references that are in the map.
- First posted on arXiv 19 Apr 2026.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT](https://mlsanity.com/paper/1904.09077/) (2019)
- [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://mlsanity.com/paper/2008.00401/) (2020)
- [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)
- [MADLAD-400: A Multilingual And Document-Level Large Audited Dataset](https://mlsanity.com/paper/2309.04662/) (2023)
- [How do Large Language Models Handle Multilingualism?](https://mlsanity.com/paper/2402.18815/) (2024)
- [What's In My Big Data?](https://mlsanity.com/paper/2310.20707/) (2023)
- [Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs](https://mlsanity.com/paper/2309.07311/) (2023)
- [Language Contamination Helps Explain the Cross-lingual Capabilities of English Pretrained Models](https://mlsanity.com/paper/2204.08110/) (2022)
- [MultiBLiMP 1.0: A Massively Multilingual Benchmark of Linguistic Minimal Pairs](https://mlsanity.com/paper/2504.02768/) (2025)
- [Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM's Translation Capability](https://mlsanity.com/paper/2305.10266/) (2023)
- [Tokenization Impacts Multilingual Language Modeling: Assessing Vocabulary Allocation and Overlap Across Languages](https://mlsanity.com/paper/2305.17179/) (2023)
- [Towards a Common Understanding of Contributing Factors for Cross-Lingual Transfer in Multilingual Language Models: A Review](https://mlsanity.com/paper/2305.16768/) (2023)
- [Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers](https://mlsanity.com/paper/2411.08745/) (2024)
- [Enhancing Multilingual LLM Pretraining with Model-Based Data Selection](https://mlsanity.com/paper/2502.10361/) (2025)
- [Understanding Cross-Lingual Alignment -- A Survey](https://mlsanity.com/paper/2404.06228/) (2024)
- [Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages](https://mlsanity.com/paper/2203.01976/) (2022)
- [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)
- [Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMT](https://mlsanity.com/paper/2109.01396/) (2021)
- [BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language Models](https://mlsanity.com/paper/2309.06085/) (2023)
- [False Friends Are Not Foes: Investigating Vocabulary Overlap in Multilingual Language Models](https://mlsanity.com/paper/2509.18750/) (2025)
- [Beyond Literal Token Overlap: Token Alignability for Multilinguality](https://mlsanity.com/paper/2502.06468/) (2025)
- [The Unreasonable Effectiveness of Model Merging for Cross-Lingual Transfer in LLMs](https://mlsanity.com/paper/2505.18356/) (2025)
- [Enhancing Translation Accuracy of Large Language Models through Continual Pre-Training on Parallel Data](https://mlsanity.com/paper/2407.03145/) (2024)

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

- [Don't Forget! Decomposing the Training Dynamics of Memorization in Language Models](https://mlsanity.com/paper/2609.34933/) (2026)

## Abstract (arXiv)

Large language models exhibit impressive cross-lingual capabilities. However, prior work analyzes this phenomenon through isolated factors and at sparse points during training, limiting our understanding of how cross-lingual generalization emerges--particularly in the early phases of learning. To study the early trajectory of linguistic and translation capabilities, we pretrain a multilingual 1.7B model on nine diverse languages, capturing checkpoints at a much finer granularity. We use word-level translation as a testbed, introducing a novel dataset to trace how translation develops over training through behavioral analyses, model-component analysis, and parameter-based ablations. We find that the model quickly acquires basic linguistic capabilities in parallel with token-level copying, while translation develops in two distinct phases: an initial phase dominated by copying and surface-level similarities, and a second phase in which more generalizing translation mechanisms are developed while copying is refined. Together, these findings provide a fine-grained view of how cross-lingual generalization develops during multilingual pretraining.