# Feature Interactions Reveal Linguistic Structure in Language Models

arXiv: https://arxiv.org/abs/2306.12181 · HTML: https://mlsanity.com/paper/2306.12181/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 66 references that are in the map.
- First posted on arXiv 21 Jun 2023.

## Builds on (most cited first, 30 of 46)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [A Benchmark for Interpretability Methods in Deep Neural Networks](https://mlsanity.com/paper/1806.10758/) (2018)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [Consistent Individualized Feature Attribution for Tree Ensembles](https://mlsanity.com/paper/1802.03888/) (2018)
- [Explaining by Removing: A Unified Framework for Model Explanation](https://mlsanity.com/paper/2011.14878/) (2020)
- [Explaining individual predictions when features are dependent: More accurate approximations to Shapley values](https://mlsanity.com/paper/1903.10464/) (2019)
- [Feature relevance quantification in explainable AI: A causal problem](https://mlsanity.com/paper/1910.13413/) (2019)
- [Measuring Association Between Labels and Free-Text Rationales](https://mlsanity.com/paper/2010.12762/) (2020)
- [A Diagnostic Study of Explainability Techniques for Text Classification](https://mlsanity.com/paper/2009.13295/) (2020)
- [The Shapley Taylor Interaction Index](https://mlsanity.com/paper/1902.05622/) (2019)
- [True to the Model or True to the Data?](https://mlsanity.com/paper/2006.16234/) (2020)
- [Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability](https://mlsanity.com/paper/1910.06358/) (2019)
- [Learning to Faithfully Rationalize by Construction](https://mlsanity.com/paper/2005.00115/) (2020)
- [Explaining Explanations: Axiomatic Feature Interactions for Deep Networks](https://mlsanity.com/paper/2002.04138/) (2020)
- [Interpreting Language Models with Contrastive Explanations](https://mlsanity.com/paper/2202.10419/) (2022)
- [Detecting Statistical Interactions from Neural Network Weights](https://mlsanity.com/paper/1705.04977/) (2017)
- [Aligning Faithful Interpretations with their Social Attribution](https://mlsanity.com/paper/2006.01067/) (2020)
- [How does this interaction affect me? Interpretable attribution for feature interactions](https://mlsanity.com/paper/2006.10965/) (2020)
- [Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs](https://mlsanity.com/paper/1801.05453/) (2018)
- [Hierarchical interpretations for neural network predictions](https://mlsanity.com/paper/1806.05337/) (2018)
- ["Will You Find These Shortcuts?" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification](https://mlsanity.com/paper/2111.07367/) (2021)

## Built on by (most cited first, 8 of 8)

- [DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers](https://mlsanity.com/paper/2310.03686/) (2023)
- [Do Language Models Exhibit Human-like Structural Priming Effects?](https://mlsanity.com/paper/2406.04847/) (2024)
- [Transparency at the Source: Evaluating and Interpreting Language Models With Access to the True Distribution](https://mlsanity.com/paper/2310.14840/) (2023)
- [Natural Language Processing RELIES on Linguistics](https://mlsanity.com/paper/2405.05966/) (2024)
- [Attribution and Alignment: Effects of Local Context Repetition on Utterance Production and Comprehension in Dialogue](https://mlsanity.com/paper/2311.13061/) (2023)
- [The Role of Syntactic Span Preferences in Post-Hoc Explanation Disagreement](https://mlsanity.com/paper/2403.19424/) (2024)
- [Using Shapley interactions to understand how models use structure](https://mlsanity.com/paper/2403.13106/) (2024)
- [The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models](https://mlsanity.com/paper/2601.19926/) (2026)

## Abstract (arXiv)

We study feature interactions in the context of feature attribution methods for post-hoc interpretability. In interpretability research, getting to grips with feature interactions is increasingly recognised as an important challenge, because interacting features are key to the success of neural networks. Feature interactions allow a model to build up hierarchical representations for its input, and might provide an ideal starting point for the investigation into linguistic structure in language models. However, uncovering the exact role that these interactions play is also difficult, and a diverse range of interaction attribution methods has been proposed. In this paper, we focus on the question which of these methods most faithfully reflects the inner workings of the target models. We work out a grey box methodology, in which we train models to perfection on a formal language classification task, using PCFGs. We show that under specific configurations, some methods are indeed able to uncover the grammatical rules acquired by a model. Based on these findings we extend our evaluation to a case study on language models, providing novel insights into the linguistic structure that these models have acquired.