# Considering Likelihood in NLP Classification Explanations with Occlusion and Language Modeling

arXiv: https://arxiv.org/abs/2004.09890 · HTML: https://mlsanity.com/paper/2004.09890/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Apr 2020.

## Built on by (most cited first, 11 of 11)

- [Connecting Attributions and QA Model Behavior on Realistic Counterfactuals](https://mlsanity.com/paper/2104.04515/) (2021)
- [Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech Detection](https://mlsanity.com/paper/2205.03302/) (2022)
- [PredDiff: Explanations and Interactions from Conditional Expectations](https://mlsanity.com/paper/2102.13519/) (2021)
- [Token-Modification Adversarial Attacks for Natural Language Processing: A Survey](https://mlsanity.com/paper/2103.00676/) (2021)
- [Efficient Explanations from Empirical Explainers](https://mlsanity.com/paper/2103.15429/) (2021)
- [Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?](https://mlsanity.com/paper/2110.11929/) (2021)
- [Adv-OLM: Generating Textual Adversaries via OLM](https://mlsanity.com/paper/2101.08523/) (2021)
- [Explaining Natural Language Processing Classifiers with Occlusion and Language Modeling](https://mlsanity.com/paper/2101.11889/) (2021)
- [XPASC: Measuring Generalization in Weak Supervision by Explainability and Association](https://mlsanity.com/paper/2206.01444/) (2022)
- [What Do Agents Communicate? Characterizing Information Exchange in Multi-Agent Systems](https://mlsanity.com/paper/2605.20548/) (2026)
- [Empowering Prior to Court Legal Analysis: A Transparent and Accessible Dataset for Defensive Statement Classification and Interpretation](https://mlsanity.com/paper/2405.10702/) (2024)

## Abstract (arXiv)

Recently, state-of-the-art NLP models gained an increasing syntactic and semantic understanding of language, and explanation methods are crucial to understand their decisions. Occlusion is a well established method that provides explanations on discrete language data, e.g. by removing a language unit from an input and measuring the impact on a model's decision. We argue that current occlusion-based methods often produce invalid or syntactically incorrect language data, neglecting the improved abilities of recent NLP models. Furthermore, gradient-based explanation methods disregard the discrete distribution of data in NLP. Thus, we propose OLM: a novel explanation method that combines occlusion and language models to sample valid and syntactically correct replacements with high likelihood, given the context of the original input. We lay out a theoretical foundation that alleviates these weaknesses of other explanation methods in NLP and provide results that underline the importance of considering data likelihood in occlusion-based explanation.