# Automata Extraction from Transformers

arXiv: https://arxiv.org/abs/2406.05564 · HTML: https://mlsanity.com/paper/2406.05564/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 8 Jun 2024.

## Builds on (most cited first, 17 of 17)

- [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)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [Learning Deep Transformer Models for Machine Translation](https://mlsanity.com/paper/1906.01787/) (2019)
- [What Formal Languages Can Transformers Express? A Survey](https://mlsanity.com/paper/2311.00208/) (2023)
- [Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition](https://mlsanity.com/paper/1402.1128/) (2014)
- [Formal Language Recognition by Hard Attention Transformers: Perspectives from Circuit Complexity](https://mlsanity.com/paper/2204.06618/) (2022)
- [Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples](https://mlsanity.com/paper/1711.09576/) (2017)
- [Weighted Automata Extraction from Recurrent Neural Networks via Regression on State Spaces](https://mlsanity.com/paper/1904.02931/) (2019)
- [Extracting Weighted Finite Automata from Recurrent Neural Networks for Natural Languages](https://mlsanity.com/paper/2206.14621/) (2022)
- [Weighted Automata Extraction and Explanation of Recurrent Neural Networks for Natural Language Tasks](https://mlsanity.com/paper/2306.14040/) (2023)

## Built on by (most cited first, 1 of 1)

- [Causal Abstraction in Model Interpretability: A Compact Survey](https://mlsanity.com/paper/2410.20161/) (2024)

## Abstract (arXiv)

In modern machine (ML) learning systems, Transformer-based architectures have achieved milestone success across a broad spectrum of tasks, yet understanding their operational mechanisms remains an open problem. To improve the transparency of ML systems, automata extraction methods, which interpret stateful ML models as automata typically through formal languages, have proven effective for explaining the mechanism of recurrent neural networks (RNNs). However, few works have been applied to this paradigm to Transformer models. In particular, understanding their processing of formal languages and identifying their limitations in this area remains unexplored. In this paper, we propose an automata extraction algorithm specifically designed for Transformer models. Treating the Transformer model as a black-box system, we track the model through the transformation process of their internal latent representations during their operations, and then use classical pedagogical approaches like L* algorithm to interpret them as deterministic finite-state automata (DFA). Overall, our study reveals how the Transformer model comprehends the structure of formal languages, which not only enhances the interpretability of the Transformer-based ML systems but also marks a crucial step toward a deeper understanding of how ML systems process formal languages. Code and data are available at https://github.com/Zhang-Yihao/Transfomer2DFA.