{"total":499,"rows":[{"id":"2202.06861","title":"Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond","created":"2022-02-14","cited_by_count":171,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2206.11104","title":"OpenXAI: Towards a Transparent Evaluation of Model Explanations","created":"2022-06-22","cited_by_count":126,"area":null},{"id":"2105.04289","title":"Do Concept Bottleneck Models Learn as Intended?","created":"2021-05-10","cited_by_count":116,"area":null},{"id":"2405.13954","title":"What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions","created":"2024-05-22","cited_by_count":94,"area":null},{"id":"2304.06819","title":"Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction","created":"2023-04-13","cited_by_count":92,"area":null},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2302.13942","title":"Inseq: An Interpretability Toolkit for Sequence Generation Models","created":"2023-02-27","cited_by_count":78,"area":null},{"id":"2206.01254","title":"Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations","created":"2022-06-02","cited_by_count":77,"area":null},{"id":"2111.14338","title":"Improving Deep Learning Interpretability by Saliency Guided Training","created":"2021-11-29","cited_by_count":68,"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":"2209.11222","title":"Concept Activation Regions: A Generalized Framework For Concept-Based Explanations","created":"2022-09-22","cited_by_count":57,"area":null},{"id":"2301.00557","title":"Learning to Maximize Mutual Information for Dynamic Feature Selection","created":"2023-01-02","cited_by_count":56,"area":null},{"id":"2312.14183","title":"On Early Detection of Hallucinations in Factual Question Answering","created":"2023-12-19","cited_by_count":56,"area":null},{"id":"2106.13200","title":"Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy","created":"2021-06-24","cited_by_count":55,"area":null},{"id":"2202.05656","title":"Evaluation of post-hoc interpretability methods in time-series classification","created":"2022-02-11","cited_by_count":53,"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":"2507.16991","title":"PyG 2.0: Scalable Learning on Real World Graphs","created":"2025-07-22","cited_by_count":52,"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":"2410.01649","title":"shapiq: Shapley Interactions for Machine Learning","created":"2024-10-02","cited_by_count":43,"area":null},{"id":"2306.02109","title":"Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency","created":"2023-06-03","cited_by_count":42,"area":null},{"id":"2205.07277","title":"Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanations","created":"2022-05-15","cited_by_count":40,"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":"2307.05916","title":"SwiFT: Swin 4D fMRI Transformer","created":"2023-07-12","cited_by_count":36,"area":null},{"id":"2203.08055","title":"Modular and Parameter-Efficient Multimodal Fusion with Prompting","created":"2022-03-15","cited_by_count":35,"area":null},{"id":"2412.18148","title":"Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media","created":"2024-12-24","cited_by_count":35,"area":null},{"id":"2207.04043","title":"The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applications","created":"2022-07-08","cited_by_count":33,"area":null},{"id":"2209.10222","title":"Fairness Reprogramming","created":"2022-09-21","cited_by_count":33,"area":null},{"id":"2302.00456","title":"Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention Maps","created":"2023-02-01","cited_by_count":33,"area":null},{"id":"2312.05491","title":"Using Captum to Explain Generative Language Models","created":"2023-12-09","cited_by_count":33,"area":null},{"id":"2112.08802","title":"UNIREX: A Unified Learning Framework for Language Model Rationale Extraction","created":"2021-12-16","cited_by_count":32,"area":null},{"id":"2301.08110","title":"AtMan: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation","created":"2023-01-19","cited_by_count":31,"area":null},{"id":"2108.04990","title":"Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing","created":"2021-08-11","cited_by_count":30,"area":null},{"id":"2107.09234","title":"Shared Interest: Measuring Human-AI Alignment to Identify Recurring Patterns in Model Behavior","created":"2021-07-20","cited_by_count":29,"area":null},{"id":"2204.01734","title":"On Explaining Multimodal Hateful Meme Detection Models","created":"2022-04-04","cited_by_count":29,"area":null},{"id":"2208.09418","title":"SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability","created":"2022-08-19","cited_by_count":28,"area":null},{"id":"2401.06654","title":"Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarks","created":"2024-01-12","cited_by_count":28,"area":null},{"id":"2406.18841","title":"Navigating LLM Ethics: Advancements, Challenges, and Future Directions","created":"2024-05-14","cited_by_count":28,"area":null},{"id":"2107.14317","title":"Temporal Dependencies in Feature Importance for Time Series Predictions","created":"2021-07-29","cited_by_count":27,"area":null},{"id":"2305.14133","title":"Conditional Mutual Information for Disentangled Representations in Reinforcement Learning","created":"2023-05-23","cited_by_count":27,"area":null},{"id":"2104.01375","title":"Evaluating explainable artificial intelligence methods for multi-label deep learning classification tasks in remote sensing","created":"2021-04-03","cited_by_count":26,"area":null},{"id":"2208.01575","title":"ferret: a Framework for Benchmarking Explainers on Transformers","created":"2022-08-02","cited_by_count":26,"area":null},{"id":"2212.14855","title":"Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces","created":"2022-12-30","cited_by_count":25,"area":null},{"id":"2412.05152","title":"Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation","created":"2024-12-06","cited_by_count":25,"area":null},{"id":"2206.04394","title":"Xplique: A Deep Learning Explainability Toolbox","created":"2022-06-09","cited_by_count":24,"area":null},{"id":"2109.02738","title":"Does BERT Learn as Humans Perceive? Understanding Linguistic Styles through Lexica","created":"2021-09-06","cited_by_count":23,"area":null},{"id":"2103.11257","title":"Robust Models Are More Interpretable Because Attributions Look Normal","created":"2021-03-20","cited_by_count":21,"area":null},{"id":"2210.07207","title":"Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation","created":"2022-10-13","cited_by_count":21,"area":null},{"id":"2109.15035","title":"Focus! Rating XAI Methods and Finding Biases","created":"2021-09-28","cited_by_count":20,"area":null},{"id":"2303.02794","title":"CoRTX: Contrastive Framework for Real-time Explanation","created":"2023-03-05","cited_by_count":20,"area":null},{"id":"2202.12270","title":"Evaluating Feature Attribution Methods in the Image Domain","created":"2022-02-22","cited_by_count":19,"area":null},{"id":"2404.11534","title":"Decomposing and Editing Predictions by Modeling Model Computation","created":"2024-04-17","cited_by_count":19,"area":null},{"id":"2410.16928","title":"xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories","created":"2024-10-22","cited_by_count":19,"area":null},{"id":"2211.16349","title":"BARTSmiles: Generative Masked Language Models for Molecular Representations","created":"2022-11-29","cited_by_count":18,"area":null},{"id":"2410.04555","title":"$\\texttt{dattri}$: A Library for Efficient Data Attribution","created":"2024-10-06","cited_by_count":18,"area":null},{"id":"2303.11932","title":"Studying How to Efficiently and Effectively Guide Models with Explanations","created":"2023-03-21","cited_by_count":16,"area":null},{"id":"2404.07004","title":"LM Transparency Tool: Interactive Tool for Analyzing Transformer Language Models","created":"2024-04-10","cited_by_count":16,"area":null},{"id":"2406.04280","title":"xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology","created":"2024-06-06","cited_by_count":16,"area":null},{"id":"2409.16756","title":"Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics","created":"2024-09-25","cited_by_count":16,"area":null},{"id":"2201.11239","title":"Diagnosing AI Explanation Methods with Folk Concepts of Behavior","created":"2022-01-27","cited_by_count":15,"area":null},{"id":"2204.12406","title":"A survey on attention mechanisms for medical applications: are we moving towards better algorithms?","created":"2022-04-26","cited_by_count":15,"area":null},{"id":"2311.01961","title":"Assessing Fidelity in XAI post-hoc techniques: A Comparative Study with Ground Truth Explanations Datasets","created":"2023-11-03","cited_by_count":15,"area":null},{"id":"2203.01928","title":"Label-Free Explainability for Unsupervised Models","created":"2022-03-03","cited_by_count":14,"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":"2304.06715","title":"Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance","created":"2023-04-13","cited_by_count":14,"area":null},{"id":"2410.12591","title":"Rethinking Visual Counterfactual Explanations Through Region Constraint","created":"2024-10-16","cited_by_count":14,"area":null},{"id":"2107.03844","title":"A Review of Bangla Natural Language Processing Tasks and the Utility of Transformer Models","created":"2021-07-08","cited_by_count":13,"area":null},{"id":"2111.08683","title":"Inferring halo masses with Graph Neural Networks","created":"2021-11-16","cited_by_count":13,"area":null},{"id":"2206.03178","title":"Fooling Explanations in Text Classifiers","created":"2022-06-07","cited_by_count":13,"area":null},{"id":"2206.08529","title":"Accelerating Shapley Explanation via Contributive Cooperator Selection","created":"2022-06-17","cited_by_count":13,"area":null},{"id":"2207.05566","title":"BASED-XAI: Breaking Ablation Studies Down for Explainable Artificial Intelligence","created":"2022-07-12","cited_by_count":13,"area":null},{"id":"2209.07430","title":"Machine Reading, Fast and Slow: When Do Models \"Understand\" Language?","created":"2022-09-15","cited_by_count":13,"area":null},{"id":"2305.12751","title":"Testing of Deep Reinforcement Learning Agents with Surrogate Models","created":"2023-05-22","cited_by_count":13,"area":null},{"id":"2403.13086","title":"Listenable Maps for Audio Classifiers","created":"2024-03-19","cited_by_count":13,"area":null},{"id":"2202.01337","title":"Generalizability of Machine Learning Models: Quantitative Evaluation of Three Methodological Pitfalls","created":"2022-02-01","cited_by_count":12,"area":null},{"id":"2203.12852","title":"Graph Neural Networks in Particle Physics: Implementations, Innovations, and Challenges","created":"2022-03-23","cited_by_count":12,"area":null},{"id":"2309.02160","title":"Bias Propagation in Federated Learning","created":"2023-09-05","cited_by_count":12,"area":null},{"id":"2311.06786","title":"Explainability of Vision Transformers: A Comprehensive Review and New Perspectives","created":"2023-11-12","cited_by_count":12,"area":null},{"id":"2406.08958","title":"An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Records","created":"2024-06-13","cited_by_count":12,"area":null},{"id":"2411.00715","title":"B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable","created":"2024-11-01","cited_by_count":12,"area":null},{"id":"2411.09973","title":"Establishing and Evaluating Trustworthy AI: Overview and Research Challenges","created":"2024-11-15","cited_by_count":12,"area":null},{"id":"2108.13961","title":"Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools","created":"2021-08-31","cited_by_count":11,"area":null},{"id":"2206.02958","title":"Saliency Cards: A Framework to Characterize and Compare Saliency Methods","created":"2022-06-07","cited_by_count":11,"area":null},{"id":"2305.17073","title":"NeuroX Library for Neuron Analysis of Deep NLP Models","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2310.05592","title":"InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations","created":"2023-10-09","cited_by_count":11,"area":null},{"id":"2407.19897","title":"BEExAI: Benchmark to Evaluate Explainable AI","created":"2024-07-29","cited_by_count":11,"area":null},{"id":"2105.04505","title":"Towards Benchmarking the Utility of Explanations for Model Debugging","created":"2021-05-10","cited_by_count":10,"area":null},{"id":"2202.13096","title":"Continuous Human Action Recognition for Human-Machine Interaction: A Review","created":"2022-02-26","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":"2211.02912","title":"New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound","created":"2022-11-05","cited_by_count":10,"area":null},{"id":"2308.14272","title":"Goodhart's Law Applies to NLP's Explanation Benchmarks","created":"2023-08-28","cited_by_count":10,"area":null},{"id":"2103.15429","title":"Efficient Explanations from Empirical Explainers","created":"2021-03-29","cited_by_count":9,"area":null},{"id":"2110.07120","title":"Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Tools","created":"2021-10-14","cited_by_count":9,"area":null},{"id":"2205.13042","title":"How explainable are adversarially-robust CNNs?","created":"2022-05-25","cited_by_count":9,"area":null},{"id":"2206.00759","title":"Interpretability Guarantees with Merlin-Arthur Classifiers","created":"2022-06-01","cited_by_count":9,"area":null},{"id":"2305.20052","title":"Integrated Decision Gradients: Compute Your Attributions Where the Model Makes Its Decision","created":"2023-05-31","cited_by_count":9,"area":null},{"id":"2308.11877","title":"Integrated Image and Location Analysis for Wound Classification: A Deep Learning Approach","created":"2023-08-23","cited_by_count":9,"area":null},{"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":"2408.10692","title":"Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models","created":"2024-08-20","cited_by_count":9,"area":null}],"next_cursor":"100"}