mlsanityData to 14 Oct 2026

Interpretation of Prediction Models Using the Input Gradient

arXiv 1611.07634 ↗First posted 23 Nov 2016stat.ML cs.LGcited by 24

Not on the map. Why?

Abstract (arXiv)

State of the art machine learning algorithms are highly optimized to provide the optimal prediction possible, naturally resulting in complex models. While these models often outperform simpler more interpretable models by order of magnitudes, in terms of understanding the way the model functions, we are often facing a "black box". In this paper we suggest a simple method to interpret the behavior of any predictive model, both for regression and classification. Given a particular model, the information required to interpret it can be obtained by studying the partial derivatives of the model with respect to the input. We exemplify this insight by interpreting convolutional and multi-layer neural networks in the field of natural language processing.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). First posted on arXiv 23 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 6; 2023: 3; 2024: 5; 2025: 2; 2026: 2.

24 papers.

Sort:

By area:

  1. 2021Order in the Court: Explainable AI Methods Prone to Disagreementcited by 36
  2. 2023Learning by Self-Explainingcited by 17
  3. 2023Interpretation of Time-Series Deep Models: A Surveycited by 15
  4. 2022A Song of (Dis)agreement: Evaluating the Evaluation of Explainable Artificial Intelligence in Natural Language Processingcited by 13
  5. 2021Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Maskscited by 12
  6. 2021Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attributioncited by 10
  7. 2022A Typology for Exploring the Mitigation of Shortcut Behaviorcited by 7
  8. 2024PromptExp: Multi-granularity Prompt Explanation of Large Language Modelscited by 6
  9. 2021Deep neural networks with controlled variable selection for the identification of putative causal genetic variantscited by 4
  10. 2025Faster Verified Explanations for Neural Networkscited by 4
  11. 2024Evaluating the Reliability of Self-Explanations in Large Language Modelscited by 3
  12. 2021Making Document-Level Information Extraction Right for the Right Reasonscited by 2
12 more
  1. 2022Identifying the Source of Vulnerability in Explanation Discrepancy: A Case Study in Neural Text Classificationcited by 2
  2. 2023One Explanation Does Not Fit XILcited by 2
  3. 2024The Conformer Encoder May Reverse the Time Dimensioncited by 2
  4. 2021Look Who's Talking: Interpretable Machine Learning for Assessing Italian SMEs Credit Defaultcited by 1
  5. 2022Interpretable Research Replication Prediction via Variational Contextual Consistency Sentence Maskingcited by 1
  6. 2022Model interpretation using improved local regression with variable importancecited by 0
  7. 2022Abstract Interpretation-Based Feature Importance for SVMscited by 0
  8. 2024Regression Trees Know Calculuscited by 0
  9. 2024CatNet: Controlling the False Discovery Rate in LSTM with SHAP Feature Importance and Gaussian Mirrorscited by 0
  10. 2025MASE: Interpretable NLP Models via Model-Agnostic Saliency Estimationcited by 0
  11. 2026Real-Time Visual Attribution Streaming in Thinking Modelcited by 0
  12. 2026Model-Agnostic FDR Control via Group Gaussian Mirror and Permutation SHAPcited by 0