# Similarity of Sentence Representations in Multilingual LMs: Resolving Conflicting Literature and Case Study of Baltic Languages

arXiv: https://arxiv.org/abs/2109.01207 · HTML: https://mlsanity.com/paper/2109.01207/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 14 references that are in the map.
- First posted on arXiv 2 Sep 2021.

## Builds on (most cited first, 9 of 9)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (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)
- [Insights on representational similarity in neural networks with canonical correlation](https://mlsanity.com/paper/1806.05759/) (2018)
- [XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation](https://mlsanity.com/paper/2004.01401/) (2020)
- [Emerging Cross-lingual Structure in Pretrained Language Models](https://mlsanity.com/paper/1911.01464/) (2019)
- [First Align, then Predict: Understanding the Cross-Lingual Ability of Multilingual BERT](https://mlsanity.com/paper/2101.11109/) (2021)

## Built on by (most cited first, 6 of 6)

- [The Same But Different: Structural Similarities and Differences in Multilingual Language Modeling](https://mlsanity.com/paper/2410.09223/) (2024)
- [Probing LLMs for Joint Encoding of Linguistic Categories](https://mlsanity.com/paper/2310.18696/) (2023)
- [Cross-lingual Similarity of Multilingual Representations Revisited](https://mlsanity.com/paper/2212.01924/) (2022)
- [Mitigating the Linguistic Gap with Phonemic Representations for Robust Cross-lingual Transfer](https://mlsanity.com/paper/2402.14279/) (2024)
- [Temporal reasoning for timeline summarisation in social media](https://mlsanity.com/paper/2501.00152/) (2024)
- [Uncovering the Potential Risks in Unlearning: Danger of English-only Unlearning in Multilingual LLMs](https://mlsanity.com/paper/2510.23949/) (2025)

## Abstract (arXiv)

Low-resource languages, such as Baltic languages, benefit from Large Multilingual Models (LMs) that possess remarkable cross-lingual transfer performance capabilities. This work is an interpretation and analysis study into cross-lingual representations of Multilingual LMs. Previous works hypothesized that these LMs internally project representations of different languages into a shared cross-lingual space. However, the literature produced contradictory results. In this paper, we revisit the prior work claiming that "BERT is not an Interlingua" and show that different languages do converge to a shared space in such language models with another choice of pooling strategy or similarity index. Then, we perform cross-lingual representational analysis for the two most popular multilingual LMs employing 378 pairwise language comparisons. We discover that while most languages share joint cross-lingual space, some do not. However, we observe that Baltic languages do belong to that shared space. The code is available at https://github.com/TartuNLP/xsim.