Gradient-Based Attribution

Ask about this topic

Overview

Gradient-based attribution studies how changes to inputs, internal representations, model parameters, or training examples affect a model’s outputs. Common approaches include saliency maps, Integrated Gradients and its path-based variants, class activation maps, and gradient-based influence methods for tracing training data or identifying important parameters. Researchers apply them to images, text, graphs, time series, and large language models, evaluating explanations with localization, deletion, faithfulness, robustness, and known-ground-truth benchmarks. A central tension is that gradients are efficient and broadly applicable, but their results can depend strongly on baselines, architectures, training choices, and evaluation metrics, so predictive accuracy alone does not establish that an attribution is faithful.

Latest papers

CardsList

113 papers15 papers in the last four weeks, up 50% on the four weeks before. 0.1% of all new papers.

  1. End-to-end Feature Alignment: A Simple CNN with Intrinsic Class Attribution

    Mar 26, 2026Parniyan Farvardin, David ChapmanNeural Network InterpretabilityExplainable Image Classification

    University of Miami

  2. No Single Metric Tells the Whole Story: A Multi-Dimensional Evaluation Framework for Uncertainty Attributions

    Mar 25, 2026Emily Schiller, Teodor Chiaburu, Marco Zullich +1Explainability EvaluationUncertainty Quantification

    XITASO GmbH IT & Software Solutions, Augsburg, Germany · The Artificial Intelligence and Cognitive Load Research Lab, University College Cork · Berliner Hochschule für Technik, Berlin, Germany +2

  3. Combi-CAM: A Novel Multi-Layer Approach for Explainable Image Geolocalization

    Mar 25, 2026David Faget, José Luis Lisani, Miguel ColomFeature AttributionGradient-Based Attribution

    CB · Centre Borelli, ENS Paris-Saclay, Université de Paris, CNRS, INSERM, SSA, France · CB, CMLA +1

  4. Toward Faithful Segmentation Attribution via Benchmarking and Dual-Evidence Fusion

    Mar 23, 2026Abu Noman Md Sakib, OFM Riaz Rahman Aranya, Kevin Desai +1Feature AttributionExplainability Evaluation

    The University of Texas at San Antonio

  5. CREG: Compass Relational Evidence Graph for Characterizing Directional Structure in VLM Spatial-Reasoning Attribution

    Mar 20, 2026Kaizhen Tan, Yang Feng, Heqing DuVLM EvaluationGradient-Based Attribution

    Carnegie Mellon University Pittsburgh, PA, USA · Columbia University New York, NY, USA

  6. GradCFA: A Hybrid Gradient-Based Counterfactual and Feature Attribution Explanation Algorithm for Local Interpretation of Neural Networks

    Mar 16, 2026Jacob Sanderson, Hua Mao, Wai Lok WooCounterfactual ExplanationsNeural Network Interpretability

    Department of Computer and Information Sciences, Northumbria University, Newcastle, UK, NE1 8ST

  7. Gradient Atoms: Unsupervised Discovery, Attribution and Steering of Model Behaviors via Sparse Decomposition of Training Gradients

    Mar 15, 2026J RosserGradient-Based AttributionTraining Data Attribution

    FLAIR, University of Oxford

  8. Understanding the Emergence of Seemingly Useless Features in Next-Token Predictors

    Mar 14, 2026Mark Rofin, Jalal Naghiyev, Michael HahnTransformer InterpretabilityLLM Interpretability

    School of Computer and Communication Sciences, EPFL · Technical University of Munich · Zuse School ELIZA +1

  9. Evaluating Explainable AI Attribution Methods in Neural Machine Translation via Attention-Guided Knowledge Distillation

    Mar 11, 2026Aria Nourbakhsh, Salima Lamsiyah, Adelaide Danilov +1Attention-Guided DistillationExplainability Evaluation

    Department of Computer Science, University of Luxembourg, 4364 Esch-sur-Alzette, Luxembourg

  10. Procedural Fairness via Group Counterfactual Explanation

    Mar 11, 2026Gideon Popoola, John SheppardAlgorithmic FairnessGroup Fairness

    Gianforte School of Computing, Montana State University, Bozeman, MT, USA

  11. Training for Trustworthy Saliency Maps: Adversarial Training Meets Feature-Map Smoothing

    Mar 7, 2026Dipkamal Bhusal, Md Tanvirul Alam, Nidhi RastogiGradient-Based AttributionExplanation Stability

    Rochester Institute of Technology

  12. Fusion-CAM: Integrating Gradient and Region-Based Class Activation Maps for Robust Visual Explanations

    Mar 5, 2026Hajar Dekdegue, Moncef Garouani, Josiane Mothe +1Explainable Image ClassificationFeature Attribution

    IRIT, UMR5505 CNRS Universit´e de Toulouse · IRIT, UMR5505 CNRS Universit´e Toulouse Capitole · INRAE, Centre Occitanie-Toulouse Unit´e Exp´erimentale APC

  13. Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis

    Feb 22, 2026Shrestha Datta, Hongfu Liu, Anshuman ChhabraKnowledge EditingLanguage Model Editing

    University of South Florida, Tampa, FL, USA · Brandeis University, Waltham, MA, USA

  14. Explainable AI: Context-Aware Layer-Wise Integrated Gradients for Explaining Transformer Models

    Feb 18, 2026Melkamu Abay Mersha, Jugal KalitaTransformer InterpretabilityGradient-Based Attribution

    College of Engineering and Applied Science, University of Colorado Colorado Springs, Colorado Springs, 80918, CO, USA

  15. Explainability for Fault Detection System in Chemical Processes

    Feb 18, 2026Georgios Gravanis, Dimitrios Kyriakou, Spyros Voutetakis +2Industrial Fault DiagnosisFault Diagnosis

    Department of Information and Electronic Engineering, International Hellenic University, Greece · Chemical Process and Energy Resources Institute, Centre for Research and Technology Hellas, Greece · Department of Industrial Engineering and Management, International Hellenic University, Greece

  16. LoRIF: Pushing the Scalability Frontier of Training Data Attribution

    Jan 29, 2026Shuangqi Li, Hieu Le, Jingyi Xu +1Training Data AttributionGradient-Based Attribution

    EPFL, Switzerland · UNC Charlotte, USA · Stony Brook University, USA

  17. Quantifying Retriever-Generator Alignment in RAG with Local Explanations

    Jan 29, 2026Korbinian Randl, Guido Rocchietti, Aron Henriksson +3Gradient-Based AttributionRetrieval-Augmented Generation

    Department of Computer and Systems Sciences, Stockholm University, Sweden · BIFOLD, Technische Universität Berlin, Germany · Department of Informatics, Athens University of Economics and Business, Greece +1

  18. Jacobian Scopes: A Unified Geometric Framework for Token-Level LLM Attribution

    Jan 23, 2026Toni J. B. Liu, Baran Zadeoğlu, Gurbir Arora +3LLM InterpretabilityGradient-Based Attribution

    ∗Cornell University, USA · ‡Goodfire AI, USA · †Imperial College London, UK

  19. Motion Attribution for Video Generation

    Jan 13, 2026Xindi Wu, Despoina Paschalidou, Jun Gao +5Gradient-Based AttributionFeature Attribution

    NVIDIA · Princeton University · University of Michigan +3

  20. Attribution Graphs and Causal Probing for Mechanistic Discovery and Bias Repair in Multimodal Generative Learning

    Oct 14, 2025Noor Islam S. Mohammad, Uluğ BayazıtGradient-Based AttributionCausal Representation Learning

    1,2Istanbul Technical University

  21. Grad-CAM for Visualizing Attention Regions of PCA and SVM Layers in Convolutional Neural Networks

    Aug 16, 2025Yuto Omae, Hirotaka TakahashiGradient-Based AttributionConvolutional Neural Networks

    Nihon University

  22. Adaptive GoGI-Skip: Coupling Goal-Gradient Importance with Dynamic Uncertainty for Efficient Reasoning

    May 13, 2025Ren ZhuangGradient-Based AttributionLLM Pruning

    School of Information Science and Technology, Hangzhou Normal University

  23. CHAOSMINING: Benchmarking Post-Hoc Attribution with Sparse Informative Features in High Dimensions

    Jun 17, 2024Ge Shi, Fangyi Liu, Ziwen Kan +1Gradient-Based AttributionFeature Attribution

    Department of Computer Science University of California, Davis