# Universal and Independent: Multilingual Probing Framework for Exhaustive Model Interpretation and Evaluation

arXiv: https://arxiv.org/abs/2210.13236 · HTML: https://mlsanity.com/paper/2210.13236/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 24 Oct 2022.

## Builds on (most cited first, 20 of 20)

- [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)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [How multilingual is Multilingual BERT?](https://mlsanity.com/paper/1906.01502/) (2019)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT](https://mlsanity.com/paper/1904.09077/) (2019)
- [SentEval: An Evaluation Toolkit for Universal Sentence Representations](https://mlsanity.com/paper/1803.05449/) (2018)
- [Post-hoc Interpretability for Neural NLP: A Survey](https://mlsanity.com/paper/2108.04840/) (2021)
- [Finding Universal Grammatical Relations in Multilingual BERT](https://mlsanity.com/paper/2005.04511/) (2020)
- [AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models](https://mlsanity.com/paper/1909.09251/) (2019)
- [Discourse Probing of Pretrained Language Models](https://mlsanity.com/paper/2104.05882/) (2021)
- [NeuroX: A Toolkit for Analyzing Individual Neurons in Neural Networks](https://mlsanity.com/paper/1812.09359/) (2018)
- [LINSPECTOR: Multilingual Probing Tasks for Word Representations](https://mlsanity.com/paper/1903.09442/) (2019)
- [Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representations](https://mlsanity.com/paper/2109.05958/) (2021)
- [Probing Multilingual Sentence Representations With X-Probe](https://mlsanity.com/paper/1906.05061/) (2019)
- [Probing Multilingual Language Models for Discourse](https://mlsanity.com/paper/2106.04832/) (2021)
- [RuSentEval: Linguistic Source, Encoder Force!](https://mlsanity.com/paper/2103.00573/) (2021)
- [Is neural language acquisition similar to natural? A chronological probing study](https://mlsanity.com/paper/2207.00560/) (2022)

## Built on by (most cited first, 3 of 3)

- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [RuBLiMP: Russian Benchmark of Linguistic Minimal Pairs](https://mlsanity.com/paper/2406.19232/) (2024)
- [Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Models](https://mlsanity.com/paper/2403.12809/) (2024)

## Abstract (arXiv)

Linguistic analysis of language models is one of the ways to explain and describe their reasoning, weaknesses, and limitations. In the probing part of the model interpretability research, studies concern individual languages as well as individual linguistic structures. The question arises: are the detected regularities linguistically coherent, or on the contrary, do they dissonate at the typological scale? Moreover, the majority of studies address the inherent set of languages and linguistic structures, leaving the actual typological diversity knowledge out of scope. In this paper, we present and apply the GUI-assisted framework allowing us to easily probe a massive number of languages for all the morphosyntactic features present in the Universal Dependencies data. We show that reflecting the anglo-centric trend in NLP over the past years, most of the regularities revealed in the mBERT model are typical for the western-European languages. Our framework can be integrated with the existing probing toolboxes, model cards, and leaderboards, allowing practitioners to use and share their standard probing methods to interpret multilingual models. Thus we propose a toolkit to systematize the multilingual flaws in multilingual models, providing a reproducible experimental setup for 104 languages and 80 morphosyntactic features. https://github.com/AIRI-Institute/Probing_framework