# Exploring Multilingual Probing in Large Language Models: A Cross-Language Analysis

arXiv: https://arxiv.org/abs/2409.14459 · HTML: https://mlsanity.com/paper/2409.14459/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 19 references that are in the map.
- First posted on arXiv 22 Sep 2024.

## Builds on (most cited first, 15 of 15)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [Do Llamas Work in English? On the Latent Language of Multilingual Transformers](https://mlsanity.com/paper/2402.10588/) (2024)
- [Information-Theoretic Probing for Linguistic Structure](https://mlsanity.com/paper/2004.03061/) (2020)
- [Towards a Cleaner Document-Oriented Multilingual Crawled Corpus](https://mlsanity.com/paper/2201.06642/) (2022)
- [Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models](https://mlsanity.com/paper/2310.10378/) (2023)
- [Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages](https://mlsanity.com/paper/2305.12182/) (2023)
- [How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study](https://mlsanity.com/paper/2402.16061/) (2024)
- [Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?](https://mlsanity.com/paper/2312.03729/) (2023)
- [Shaking Syntactic Trees on the Sesame Street: Multilingual Probing with Controllable Perturbations](https://mlsanity.com/paper/2109.14017/) (2021)
- [Performance of Recent Large Language Models for a Low-Resourced Language](https://mlsanity.com/paper/2407.21330/) (2024)
- [A Survey of Large Language Models for European Languages](https://mlsanity.com/paper/2408.15040/) (2024)

## Built on by (most cited first, 12 of 12)

- [Middle-Layer Representation Alignment for Cross-Lingual Transfer in Fine-Tuned LLMs](https://mlsanity.com/paper/2502.14830/) (2025)
- [MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment](https://mlsanity.com/paper/2410.05873/) (2024)
- [From Imitation to Introspection: Probing Self-Consciousness in Language Models](https://mlsanity.com/paper/2410.18819/) (2024)
- [CoCo-CoLa: Evaluating and Improving Language Adherence in Multilingual LLMs](https://mlsanity.com/paper/2502.12476/) (2025)
- [The Compositional Architecture of Regret in Large Language Models](https://mlsanity.com/paper/2506.15617/) (2025)
- [LangSAMP: Language-Script Aware Multilingual Pretraining](https://mlsanity.com/paper/2409.18199/) (2024)
- [A Shared Geometry of Difficulty in Multilingual Language Models](https://mlsanity.com/paper/2601.12731/) (2026)
- [Behavior and Representation in Open-Weight Large Language Models for Combinatorial Optimization: From Feature Extraction to Algorithm Selection](https://mlsanity.com/paper/2512.13374/) (2025)
- [Script Choice in LLMs: Evidence for Late-Layer Commitment](https://mlsanity.com/paper/2609.28784/) (2026)
- [LLM Probe: Evaluating LLMs for Low-Resource Languages](https://mlsanity.com/paper/2603.29517/) (2026)
- [Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning](https://mlsanity.com/paper/2605.14386/) (2026)
- [Cross-lingual Calibration of Pre-Generation Success Probes for Multilingual LLM Routing](https://mlsanity.com/paper/2610.06216/) (2026)

## Abstract (arXiv)

Probing techniques for large language models (LLMs) have primarily focused on English, overlooking the vast majority of the world's languages. In this paper, we extend these probing methods to a multilingual context, investigating the behaviors of LLMs across diverse languages. We conduct experiments on several open-source LLM models, analyzing probing accuracy, trends across layers, and similarities between probing vectors for multiple languages. Our key findings reveal: (1) a consistent performance gap between high-resource and low-resource languages, with high-resource languages achieving significantly higher probing accuracy; (2) divergent layer-wise accuracy trends, where high-resource languages show substantial improvement in deeper layers similar to English; and (3) higher representational similarities among high-resource languages, with low-resource languages demonstrating lower similarities both among themselves and with high-resource languages. These results highlight significant disparities in LLMs' multilingual capabilities and emphasize the need for improved modeling of low-resource languages.