# Interpreting Neural Networks With Nearest Neighbors

arXiv: https://arxiv.org/abs/1809.02847 · HTML: https://mlsanity.com/paper/1809.02847/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Sep 2018.

## Built on by (most cited first, 18 of 18)

- [Towards Faithful Model Explanation in NLP: A Survey](https://mlsanity.com/paper/2209.11326/) (2022)
- [ConvFiT: Conversational Fine-Tuning of Pretrained Language Models](https://mlsanity.com/paper/2109.10126/) (2021)
- [On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs](https://mlsanity.com/paper/2407.19200/) (2024)
- [Interpreting Deep Learning Models in Natural Language Processing: A Review](https://mlsanity.com/paper/2110.10470/) (2021)
- [Towards Explainable Evaluation Metrics for Natural Language Generation](https://mlsanity.com/paper/2203.11131/) (2022)
- [Let the CAT out of the bag: Contrastive Attributed explanations for Text](https://mlsanity.com/paper/2109.07983/) (2021)
- [Towards flexible perception with visual memory](https://mlsanity.com/paper/2408.08172/) (2024)
- [A Neighbourhood Framework for Resource-Lean Content Flagging](https://mlsanity.com/paper/2103.17055/) (2021)
- [A Necessary Step toward Faithfulness: Measuring and Improving Consistency in Free-Text Explanations](https://mlsanity.com/paper/2505.19299/) (2025)
- [DeepEverest: Accelerating Declarative Top-K Queries for Deep Neural Network Interpretation](https://mlsanity.com/paper/2104.02234/) (2021)
- [Towards Explaining Subjective Ground of Individuals on Social Media](https://mlsanity.com/paper/2211.09953/) (2022)
- [Optimising Human-AI Collaboration by Learning Convincing Explanations](https://mlsanity.com/paper/2311.07426/) (2023)
- [Wrapper Boxes: Faithful Attribution of Model Predictions to Training Data](https://mlsanity.com/paper/2311.08644/) (2023)
- [An empirical analysis of phrase-based and neural machine translation](https://mlsanity.com/paper/2103.03108/) (2021)
- [Task-Specific Embeddings for Ante-Hoc Explainable Text Classification](https://mlsanity.com/paper/2212.00086/) (2022)
- [Explaining high-dimensional text classifiers](https://mlsanity.com/paper/2311.13454/) (2023)
- [CELL your Model: Contrastive Explanations for Large Language Models](https://mlsanity.com/paper/2406.11785/) (2024)
- [Separating Knowledge and Perception with Procedural Data](https://mlsanity.com/paper/2508.11697/) (2025)

## Abstract (arXiv)

Local model interpretation methods explain individual predictions by assigning an importance value to each input feature. This value is often determined by measuring the change in confidence when a feature is removed. However, the confidence of neural networks is not a robust measure of model uncertainty. This issue makes reliably judging the importance of the input features difficult. We address this by changing the test-time behavior of neural networks using Deep k-Nearest Neighbors. Without harming text classification accuracy, this algorithm provides a more robust uncertainty metric which we use to generate feature importance values. The resulting interpretations better align with human perception than baseline methods. Finally, we use our interpretation method to analyze model predictions on dataset annotation artifacts.