{"total":297,"rows":[{"id":"2106.02997","title":"Causal Abstractions of Neural Networks","created":"2021-06-06","cited_by_count":422,"area":null},{"id":"2301.04709","title":"Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability","created":"2023-01-11","cited_by_count":205,"area":"mechinterp"},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2112.00826","title":"Inducing Causal Structure for Interpretable Neural Networks","created":"2021-12-01","cited_by_count":110,"area":null},{"id":"2409.00729","title":"ContextCite: Attributing Model Generation to Context","created":"2024-09-01","cited_by_count":98,"area":null},{"id":"2202.10419","title":"Interpreting Language Models with Contrastive Explanations","created":"2022-02-21","cited_by_count":92,"area":null},{"id":"2111.02398","title":"Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods","created":"2021-11-01","cited_by_count":83,"area":null},{"id":"2111.04138","title":"Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis","created":"2021-11-07","cited_by_count":65,"area":null},{"id":"2203.04212","title":"Measuring the Mixing of Contextual Information in the Transformer","created":"2022-03-08","cited_by_count":65,"area":null},{"id":"2502.20578","title":"Interpreting CLIP with Hierarchical Sparse Autoencoders","created":"2025-02-27","cited_by_count":60,"area":"mechinterp"},{"id":"2202.00734","title":"Framework for Evaluating Faithfulness of Local Explanations","created":"2022-02-01","cited_by_count":55,"area":null},{"id":"2102.12781","title":"Do Input Gradients Highlight Discriminative Features?","created":"2021-02-25","cited_by_count":52,"area":null},{"id":"2305.15853","title":"Sequential Integrated Gradients: a simple but effective method for explaining language models","created":"2023-05-25","cited_by_count":52,"area":null},{"id":"2308.06248","title":"FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods","created":"2023-08-11","cited_by_count":50,"area":null},{"id":"2104.12669","title":"Exploiting Explanations for Model Inversion Attacks","created":"2021-04-26","cited_by_count":49,"area":null},{"id":"2108.13654","title":"Discretized Integrated Gradients for Explaining Language Models","created":"2021-08-31","cited_by_count":46,"area":null},{"id":"2206.05282","title":"Learning to Estimate Shapley Values with Vision Transformers","created":"2022-06-10","cited_by_count":45,"area":null},{"id":"2305.12535","title":"Explaining How Transformers Use Context to Build Predictions","created":"2023-05-21","cited_by_count":43,"area":null},{"id":"2104.02297","title":"Shapley Explanation Networks","created":"2021-04-06","cited_by_count":41,"area":null},{"id":"2302.07265","title":"The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantus","created":"2023-02-14","cited_by_count":37,"area":null},{"id":"2111.06206","title":"Defining and Quantifying the Emergence of Sparse Concepts in DNNs","created":"2021-11-11","cited_by_count":36,"area":null},{"id":"2502.08524","title":"LLM Pretraining with Continuous Concepts","created":"2025-02-12","cited_by_count":36,"area":"lr"},{"id":"2104.14235","title":"Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety","created":"2021-04-29","cited_by_count":35,"area":null},{"id":"2111.07668","title":"Fast Axiomatic Attribution for Neural Networks","created":"2021-11-15","cited_by_count":35,"area":null},{"id":"2202.10553","title":"Guidelines and Evaluation of Clinical Explainable AI in Medical Image Analysis","created":"2022-02-16","cited_by_count":35,"area":null},{"id":"2206.06219","title":"Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure","created":"2022-06-13","cited_by_count":33,"area":null},{"id":"2301.09937","title":"Explainable Deep Reinforcement Learning: State of the Art and Challenges","created":"2023-01-24","cited_by_count":33,"area":null},{"id":"2203.12892","title":"Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals","created":"2022-03-24","cited_by_count":30,"area":null},{"id":"2202.03407","title":"Investigating the fidelity of explainable artificial intelligence methods for applications of convolutional neural networks in geoscience","created":"2022-02-07","cited_by_count":28,"area":null},{"id":"2110.04392","title":"The Eval4NLP Shared Task on Explainable Quality Estimation: Overview and Results","created":"2021-10-08","cited_by_count":27,"area":null},{"id":"2303.00652","title":"Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science","created":"2023-03-01","cited_by_count":27,"area":null},{"id":"2108.01070","title":"Finding Discriminative Filters for Specific Degradations in Blind Super-Resolution","created":"2021-08-02","cited_by_count":26,"area":null},{"id":"2109.00520","title":"The Role of Explainability in Assuring Safety of Machine Learning in Healthcare","created":"2021-09-01","cited_by_count":26,"area":null},{"id":"2203.05922","title":"Visualizing and Understanding Patch Interactions in Vision Transformer","created":"2022-03-11","cited_by_count":26,"area":null},{"id":"2202.00232","title":"Improving deep neural network generalization and robustness to background bias via layer-wise relevance propagation optimization","created":"2022-02-01","cited_by_count":25,"area":null},{"id":"2204.04908","title":"No Token Left Behind: Explainability-Aided Image Classification and Generation","created":"2022-04-11","cited_by_count":25,"area":null},{"id":"2205.14108","title":"Scalable Interpretability via Polynomials","created":"2022-05-27","cited_by_count":25,"area":null},{"id":"2207.06236","title":"Explainable Intrusion Detection Systems (X-IDS): A Survey of Current Methods, Challenges, and Opportunities","created":"2022-07-13","cited_by_count":25,"area":null},{"id":"2312.06581","title":"Grokking Group Multiplication with Cosets","created":"2023-12-11","cited_by_count":24,"area":null},{"id":"2106.08641","title":"Best of both worlds: local and global explanations with human-understandable concepts","created":"2021-06-16","cited_by_count":22,"area":null},{"id":"2203.06487","title":"Evaluating Explainable AI on a Multi-Modal Medical Imaging Task: Can Existing Algorithms Fulfill Clinical Requirements?","created":"2022-03-12","cited_by_count":20,"area":null},{"id":"2306.07462","title":"On the Robustness of Removal-Based Feature Attributions","created":"2023-06-12","cited_by_count":19,"area":null},{"id":"2310.18585","title":"Visual Explanations via Iterated Integrated Attributions","created":"2023-10-28","cited_by_count":19,"area":null},{"id":"2403.14552","title":"Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer","created":"2024-03-21","cited_by_count":19,"area":null},{"id":"2404.01415","title":"On the Faithfulness of Vision Transformer Explanations","created":"2024-04-01","cited_by_count":19,"area":null},{"id":"2103.10005","title":"Neural Network Attribution Methods for Problems in Geoscience: A Novel Synthetic Benchmark Dataset","created":"2021-03-18","cited_by_count":18,"area":null},{"id":"2607.05394","title":"Weak-to-Strong Generalization via Direct On-Policy Distillation","created":"2026-07-06","cited_by_count":18,"area":"distill"},{"id":"2203.14196","title":"HINT: Hierarchical Neuron Concept Explainer","created":"2022-03-27","cited_by_count":17,"area":null},{"id":"2304.01811","title":"HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation","created":"2023-04-04","cited_by_count":17,"area":null},{"id":"2102.07805","title":"Integrated Grad-CAM: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks via Integrated Gradient-Based Scoring","created":"2021-02-15","cited_by_count":16,"area":null},{"id":"2109.04236","title":"ECQ$^{\\text{x}}$: Explainability-Driven Quantization for Low-Bit and Sparse DNNs","created":"2021-09-09","cited_by_count":15,"area":null},{"id":"2112.02625","title":"Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution View","created":"2021-12-05","cited_by_count":15,"area":null},{"id":"2305.14582","title":"Interpretation of Time-Series Deep Models: A Survey","created":"2023-05-23","cited_by_count":15,"area":null},{"id":"2411.06090","title":"Concept Bottleneck Language Models For protein design","created":"2024-11-09","cited_by_count":15,"area":null},{"id":"2205.12423","title":"Deletion and Insertion Tests in Regression Models","created":"2022-05-25","cited_by_count":14,"area":null},{"id":"2211.14860","title":"Foiling Explanations in Deep Neural Networks","created":"2022-11-27","cited_by_count":14,"area":null},{"id":"2311.09620","title":"GAIA: Delving into Gradient-based Attribution Abnormality for Out-of-distribution Detection","created":"2023-11-16","cited_by_count":12,"area":null},{"id":"2106.07475","title":"Investigating sanity checks for saliency maps with image and text classification","created":"2021-06-08","cited_by_count":11,"area":null},{"id":"2206.09358","title":"What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs","created":"2022-06-19","cited_by_count":11,"area":null},{"id":"2303.01506","title":"Understanding and Unifying Fourteen Attribution Methods with Taylor Interactions","created":"2023-03-02","cited_by_count":11,"area":null},{"id":"2408.05506","title":"Your Context Is Not an Array: Unveiling Random Access Limitations in Transformers","created":"2024-08-10","cited_by_count":11,"area":null},{"id":"2506.12766","title":"Probing Deep into Temporal Profile Makes the Infrared Small Target Detector Much Better","created":"2025-06-15","cited_by_count":11,"area":null},{"id":"2107.07013","title":"Passive Attention in Artificial Neural Networks Predicts Human Visual Selectivity","created":"2021-07-14","cited_by_count":10,"area":null},{"id":"2204.13359","title":"Poly-CAM: High resolution class activation map for convolutional neural networks","created":"2022-04-28","cited_by_count":10,"area":null},{"id":"2307.05350","title":"Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat","created":"2023-07-07","cited_by_count":10,"area":null},{"id":"2310.15368","title":"Deep Integrated Explanations","created":"2023-10-23","cited_by_count":10,"area":null},{"id":"2312.02364","title":"Class-Discriminative Attention Maps for Vision Transformers","created":"2023-12-04","cited_by_count":10,"area":null},{"id":"2312.09783","title":"Keep the Faith: Faithful Explanations in Convolutional Neural Networks for Case-Based Reasoning","created":"2023-12-15","cited_by_count":10,"area":null},{"id":"2112.14015","title":"GuidedMix-Net: Semi-supervised Semantic Segmentation by Using Labeled Images as Reference","created":"2021-12-28","cited_by_count":9,"area":null},{"id":"2204.01719","title":"RestoreX-AI: A Contrastive Approach towards Guiding Image Restoration via Explainable AI Systems","created":"2022-04-03","cited_by_count":9,"area":null},{"id":"2211.04110","title":"Privacy Meets Explainability: A Comprehensive Impact Benchmark","created":"2022-11-08","cited_by_count":9,"area":null},{"id":"2307.13850","title":"MAEA: Multimodal Attribution for Embodied AI","created":"2023-07-25","cited_by_count":9,"area":null},{"id":"2308.00319","title":"LimeAttack: Local Explainable Method for Textual Hard-Label Adversarial Attack","created":"2023-08-01","cited_by_count":9,"area":null},{"id":"2310.19321","title":"D4Explainer: In-Distribution GNN Explanations via Discrete Denoising Diffusion","created":"2023-10-30","cited_by_count":9,"area":"diffusion"},{"id":"2401.06465","title":"Sanity Checks Revisited: An Exploration to Repair the Model Parameter Randomisation Test","created":"2024-01-12","cited_by_count":9,"area":null},{"id":"2403.02955","title":"XAI-Based Detection of Adversarial Attacks on Deepfake Detectors","created":"2024-03-05","cited_by_count":9,"area":null},{"id":"2407.03545","title":"On Evaluating Explanation Utility for Human-AI Decision Making in NLP","created":"2024-07-03","cited_by_count":9,"area":null},{"id":"2412.14056","title":"A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2105.07033","title":"Cause and Effect: Hierarchical Concept-based Explanation of Neural Networks","created":"2021-05-14","cited_by_count":8,"area":null},{"id":"2109.00928","title":"Speaker-Conditioned Hierarchical Modeling for Automated Speech Scoring","created":"2021-08-30","cited_by_count":8,"area":null},{"id":"2202.03759","title":"Time to Focus: A Comprehensive Benchmark Using Time Series Attribution Methods","created":"2022-02-08","cited_by_count":8,"area":null},{"id":"2311.16120","title":"Sanity checks for patch visualisation in prototype-based image classification","created":"2023-10-25","cited_by_count":8,"area":null},{"id":"2405.02383","title":"A Fresh Look at Sanity Checks for Saliency Maps","created":"2024-05-03","cited_by_count":8,"area":null},{"id":"2407.11910","title":"Benchmarking the Attribution Quality of Vision Models","created":"2024-07-16","cited_by_count":8,"area":null},{"id":"2409.10329","title":"InfoDisent: Explainability of Image Classification Models by Information Disentanglement","created":"2024-09-16","cited_by_count":8,"area":null},{"id":"2602.16698","title":"Causality is Key for Interpretability Claims to Generalise","created":"2026-02-18","cited_by_count":8,"area":null},{"id":"2104.07324","title":"OneLog: Towards End-to-End Training in Software Log Anomaly Detection","created":"2021-04-15","cited_by_count":7,"area":null},{"id":"2202.06948","title":"Towards Best Practice of Interpreting Deep Learning Models for EEG-based Brain Computer Interfaces","created":"2022-02-12","cited_by_count":7,"area":null},{"id":"2209.11607","title":"I-SPLIT: Deep Network Interpretability for Split Computing","created":"2022-09-23","cited_by_count":7,"area":null},{"id":"2210.16117","title":"Improving the Transferability of Adversarial Attacks on Face Recognition with Beneficial Perturbation Feature Augmentation","created":"2022-10-28","cited_by_count":7,"area":null},{"id":"2210.17376","title":"SoK: Modeling Explainability in Security Analytics for Interpretability, Trustworthiness, and Usability","created":"2022-10-31","cited_by_count":7,"area":null},{"id":"2306.02775","title":"Input-gradient space particle inference for neural network ensembles","created":"2023-06-05","cited_by_count":7,"area":null},{"id":"2307.13582","title":"Argument Attribution Explanations in Quantitative Bipolar Argumentation Frameworks (Technical Report)","created":"2023-07-25","cited_by_count":7,"area":null},{"id":"2311.01732","title":"Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Models","created":"2023-11-03","cited_by_count":7,"area":"mechinterp"},{"id":"2402.12921","title":"Right on Time: Revising Time Series Models by Constraining their Explanations","created":"2024-02-20","cited_by_count":7,"area":null},{"id":"2403.07279","title":"A Survey of Explainable Knowledge Tracing","created":"2024-03-12","cited_by_count":7,"area":null},{"id":"2404.02359","title":"Attribution Regularization for Multimodal Paradigms","created":"2024-04-02","cited_by_count":7,"area":null},{"id":"2407.09115","title":"Layer-Wise Relevance Propagation with Conservation Property for ResNet","created":"2024-07-12","cited_by_count":7,"area":null},{"id":"2504.07389","title":"Task-Circuit Quantization: Leveraging Knowledge Localization and Interpretability for Compression","created":"2025-04-10","cited_by_count":7,"area":null},{"id":"2505.12897","title":"EPIC: Explanation of Pretrained Image Classification Networks via Prototype","created":"2025-05-19","cited_by_count":7,"area":null}],"next_cursor":"100"}