# LS-Tree: Model Interpretation When the Data Are Linguistic

arXiv: https://arxiv.org/abs/1902.04187 · HTML: https://mlsanity.com/paper/1902.04187/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Feb 2019.

## Built on by (most cited first, 7 of 7)

- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Algorithms to estimate Shapley value feature attributions](https://mlsanity.com/paper/2207.07605/) (2022)
- [Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution](https://mlsanity.com/paper/2401.15866/) (2024)
- [On the Robustness of Removal-Based Feature Attributions](https://mlsanity.com/paper/2306.07462/) (2023)
- [Multi-Level Explanations for Generative Language Models](https://mlsanity.com/paper/2403.14459/) (2024)
- [Selective Explanations](https://mlsanity.com/paper/2405.19562/) (2024)
- [Order-sensitive Shapley Values for Evaluating Conceptual Soundness of NLP Models](https://mlsanity.com/paper/2206.00192/) (2022)

## Abstract (arXiv)

We study the problem of interpreting trained classification models in the setting of linguistic data sets. Leveraging a parse tree, we propose to assign least-squares based importance scores to each word of an instance by exploiting syntactic constituency structure. We establish an axiomatic characterization of these importance scores by relating them to the Banzhaf value in coalitional game theory. Based on these importance scores, we develop a principled method for detecting and quantifying interactions between words in a sentence. We demonstrate that the proposed method can aid in interpretability and diagnostics for several widely-used language models.