# A Systematic Comparison of Multilingual Interpretability Methods Reveals Anisotropy-Driven Failures

arXiv: https://arxiv.org/abs/2609.04819 · HTML: https://mlsanity.com/paper/2609.04819/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 46 references that are in the map.
- First posted on arXiv 4 Sep 2026.

## Builds on (most cited first, 29 of 29)

- [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)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [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)
- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [How multilingual is Multilingual BERT?](https://mlsanity.com/paper/1906.01502/) (2019)
- [Eliciting Latent Predictions from Transformers with the Tuned Lens](https://mlsanity.com/paper/2303.08112/) (2023)
- [On the Cross-lingual Transferability of Monolingual Representations](https://mlsanity.com/paper/1910.11856/) (2019)
- [The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants](https://mlsanity.com/paper/2308.16884/) (2023)
- [Do Llamas Work in English? On the Latent Language of Multilingual Transformers](https://mlsanity.com/paper/2402.10588/) (2024)
- [Representation Degeneration Problem in Training Natural Language Generation Models](https://mlsanity.com/paper/1907.12009/) (2019)
- [Emerging Cross-lingual Structure in Pretrained Language Models](https://mlsanity.com/paper/1911.01464/) (2019)
- [All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality](https://mlsanity.com/paper/2109.04404/) (2021)
- [SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects](https://mlsanity.com/paper/2309.07445/) (2023)
- [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)
- [Common Sense Beyond English: Evaluating and Improving Multilingual Language Models for Commonsense Reasoning](https://mlsanity.com/paper/2106.06937/) (2021)
- [Anisotropy Is Inherent to Self-Attention in Transformers](https://mlsanity.com/paper/2401.12143/) (2024)
- [IsoScore: Measuring the Uniformity of Embedding Space Utilization](https://mlsanity.com/paper/2108.07344/) (2021)
- [MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment](https://mlsanity.com/paper/2410.05873/) (2024)
- [Exploring Anisotropy and Outliers in Multilingual Language Models for Cross-Lingual Semantic Sentence Similarity](https://mlsanity.com/paper/2306.00458/) (2023)
- [Can you map it to English? The Role of Cross-Lingual Alignment in Multilingual Performance of LLMs](https://mlsanity.com/paper/2504.09378/) (2025)
- [The Role of Language Imbalance in Cross-lingual Generalisation: Insights from Cloned Language Experiments](https://mlsanity.com/paper/2404.07982/) (2024)
- [Cross-lingual Similarity of Multilingual Representations Revisited](https://mlsanity.com/paper/2212.01924/) (2022)
- [How Does Alignment Enhance LLMs' Multilingual Capabilities? A Language Neurons Perspective](https://mlsanity.com/paper/2505.21505/) (2025)
- [Tracing Multilingual Representations in LLMs with Cross-Layer Transcoders](https://mlsanity.com/paper/2511.10840/) (2025)
- [What Language(s) Does Aya-23 Think In? How Multilinguality Affects Internal Language Representations](https://mlsanity.com/paper/2507.20279/) (2025)
- [High-Dimensional Interlingual Representations of Large Language Models](https://mlsanity.com/paper/2503.11280/) (2025)

## Abstract (arXiv)

Multilingual language models develop shared cross-lingual representations, and various interpretability methods claim to quantify this sharing. These methods have been developed largely in isolation, and when they disagree, it is unclear whether the disagreement reflects a property of the model or an artifact of the measurement. We compare four sharing metrics (CKA, ANC, GMM dominance per token, and ILO) across 21 base models from five families (125M-14B parameters) and correlate each with cross-lingual transfer on five downstream tasks. We find that the metrics differ in their quantification of cross-lingual sharing in these models and suggest that the disagreement traces to anisotropy, the tendency of representations to cluster in a narrow cone of the embedding space. Only ILO's correlation with cross-lingual transfer (Spearman's ρ = 0.90) survives controls for model size, family, and per-task variation. We therefore recommend ILO as the primary sharing metric, to be reported alongside anisotropy diagnostics.