# The Role of Syntactic Span Preferences in Post-Hoc Explanation Disagreement

arXiv: https://arxiv.org/abs/2403.19424 · HTML: https://mlsanity.com/paper/2403.19424/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 45 references that are in the map.
- First posted on arXiv 28 Mar 2024.

## Builds on (most cited first, 28 of 28)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [A Diagnostic Study of Explainability Techniques for Text Classification](https://mlsanity.com/paper/2009.13295/) (2020)
- [The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective](https://mlsanity.com/paper/2202.01602/) (2022)
- [Post-hoc Interpretability for Neural NLP: A Survey](https://mlsanity.com/paper/2108.04840/) (2021)
- [Multilingual Constituency Parsing with Self-Attention and Pre-Training](https://mlsanity.com/paper/1812.11760/) (2018)
- [Faithfulness Tests for Natural Language Explanations](https://mlsanity.com/paper/2305.18029/) (2023)
- [Evaluating Explanations: How much do explanations from the teacher aid students?](https://mlsanity.com/paper/2012.00893/) (2020)
- ["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)
- [How can I choose an explainer? An Application-grounded Evaluation of Post-hoc Explanations](https://mlsanity.com/paper/2101.08758/) (2021)
- [Can I Trust the Explainer? Verifying Post-hoc Explanatory Methods](https://mlsanity.com/paper/1910.02065/) (2019)
- [Evaluating and Characterizing Human Rationales](https://mlsanity.com/paper/2010.04736/) (2020)
- [ferret: a Framework for Benchmarking Explainers on Transformers](https://mlsanity.com/paper/2208.01575/) (2022)
- [Parsing All: Syntax and Semantics, Dependencies and Spans](https://mlsanity.com/paper/1908.11522/) (2019)
- [Towards Interpreting BERT for Reading Comprehension Based QA](https://mlsanity.com/paper/2010.08983/) (2020)
- [A Song of (Dis)agreement: Evaluating the Evaluation of Explainable Artificial Intelligence in Natural Language Processing](https://mlsanity.com/paper/2205.04559/) (2022)
- [Many Faces of Feature Importance: Comparing Built-in and Post-hoc Feature Importance in Text Classification](https://mlsanity.com/paper/1910.08534/) (2019)
- [Interpretation of Black Box NLP Models: A Survey](https://mlsanity.com/paper/2203.17081/) (2022)
- [The Legal Argument Reasoning Task in Civil Procedure](https://mlsanity.com/paper/2211.02950/) (2022)
- [Feature Interactions Reveal Linguistic Structure in Language Models](https://mlsanity.com/paper/2306.12181/) (2023)
- [Dynamic Top-k Estimation Consolidates Disagreement between Feature Attribution Methods](https://mlsanity.com/paper/2310.05619/) (2023)

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

- [Short-circuiting Shortcuts: Mechanistic Investigation of Shortcuts in Text Classification](https://mlsanity.com/paper/2505.06032/) (2025)
- [Learning from Sufficient Rationales: Analysing the Relationship Between Explanation Faithfulness and Token-level Regularisation Strategies](https://mlsanity.com/paper/2511.16353/) (2025)
- [Explanation Bias is a Product: Revealing the Hidden Lexical and Position Preferences in Post-Hoc Feature Attribution](https://mlsanity.com/paper/2512.11108/) (2025)

## Abstract (arXiv)

Post-hoc explanation methods are an important tool for increasing model transparency for users. Unfortunately, the currently used methods for attributing token importance often yield diverging patterns. In this work, we study potential sources of disagreement across methods from a linguistic perspective. We find that different methods systematically select different classes of words and that methods that agree most with other methods and with humans display similar linguistic preferences. Token-level differences between methods are smoothed out if we compare them on the syntactic span level. We also find higher agreement across methods by estimating the most important spans dynamically instead of relying on a fixed subset of size k. We systematically investigate the interaction between k and spans and propose an improved configuration for selecting important tokens.