# Can BERT eat RuCoLA? Topological Data Analysis to Explain

arXiv: https://arxiv.org/abs/2304.01680 · HTML: https://mlsanity.com/paper/2304.01680/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 40 references that are in the map.
- First posted on arXiv 4 Apr 2023.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Measuring and Improving Consistency in Pretrained Language Models](https://mlsanity.com/paper/2102.01017/) (2021)
- [Revealing the Dark Secrets of BERT](https://mlsanity.com/paper/1908.08593/) (2019)
- [A Survey of the State of Explainable AI for Natural Language Processing](https://mlsanity.com/paper/2010.00711/) (2020)
- [A Diagnostic Study of Explainability Techniques for Text Classification](https://mlsanity.com/paper/2009.13295/) (2020)
- [When Do You Need Billions of Words of Pretraining Data?](https://mlsanity.com/paper/2011.04946/) (2020)
- [Artificial Text Detection via Examining the Topology of Attention Maps](https://mlsanity.com/paper/2109.04825/) (2021)
- [Automatic Text Evaluation through the Lens of Wasserstein Barycenters](https://mlsanity.com/paper/2108.12463/) (2021)
- [How transfer learning impacts linguistic knowledge in deep NLP models?](https://mlsanity.com/paper/2105.15179/) (2021)
- [How Furiously Can Colourless Green Ideas Sleep? Sentence Acceptability in Context](https://mlsanity.com/paper/2004.00881/) (2020)
- [RuCoLA: Russian Corpus of Linguistic Acceptability](https://mlsanity.com/paper/2210.12814/) (2022)
- [Linguistic Profiling of a Neural Language Model](https://mlsanity.com/paper/2010.01869/) (2020)
- [Acceptability Judgements via Examining the Topology of Attention Maps](https://mlsanity.com/paper/2205.09630/) (2022)
- [Shaking Syntactic Trees on the Sesame Street: Multilingual Probing with Controllable Perturbations](https://mlsanity.com/paper/2109.14017/) (2021)
- [BERTops: Studying BERT Representations under a Topological Lens](https://mlsanity.com/paper/2205.00953/) (2022)

## Built on by (most cited first, 5 of 5)

- [Hallucination Detection in LLMs with Topological Divergence on Attention Graphs](https://mlsanity.com/paper/2504.10063/) (2025)
- [Text summarization via global structure awareness](https://mlsanity.com/paper/2602.09821/) (2026)
- [TaeBench: Improving Quality of Toxic Adversarial Examples](https://mlsanity.com/paper/2410.05573/) (2024)
- [Topological Data Analysis Applications in Natural Language Processing: A Survey](https://mlsanity.com/paper/2411.10298/) (2024)
- [Exploring the Effectiveness of Methods for Persona Extraction](https://mlsanity.com/paper/2407.09181/) (2024)

## Abstract (arXiv)

This paper investigates how Transformer language models (LMs) fine-tuned for acceptability classification capture linguistic features. Our approach uses the best practices of topological data analysis (TDA) in NLP: we construct directed attention graphs from attention matrices, derive topological features from them, and feed them to linear classifiers. We introduce two novel features, chordality, and the matching number, and show that TDA-based classifiers outperform fine-tuning baselines. We experiment with two datasets, CoLA and RuCoLA in English and Russian, typologically different languages. On top of that, we propose several black-box introspection techniques aimed at detecting changes in the attention mode of the LMs during fine-tuning, defining the LM's prediction confidences, and associating individual heads with fine-grained grammar phenomena. Our results contribute to understanding the behavior of monolingual LMs in the acceptability classification task, provide insights into the functional roles of attention heads, and highlight the advantages of TDA-based approaches for analyzing LMs. We release the code and the experimental results for further uptake.