{"total":145,"rows":[{"id":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302,"area":null},{"id":"2205.03401","title":"The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning","created":"2022-05-06","cited_by_count":169,"area":"lr"},{"id":"2210.01790","title":"Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals","created":"2022-10-04","cited_by_count":126,"area":null},{"id":"2311.02262","title":"Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs","created":"2023-11-03","cited_by_count":91,"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":"2106.12674","title":"Fairness via Representation Neutralization","created":"2021-06-23","cited_by_count":63,"area":null},{"id":"2203.02110","title":"FairPrune: Achieving Fairness Through Pruning for Dermatological Disease Diagnosis","created":"2022-03-04","cited_by_count":59,"area":null},{"id":"2212.04629","title":"Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation","created":"2022-12-09","cited_by_count":59,"area":null},{"id":"2104.15135","title":"Explanation-Based Human Debugging of NLP Models: A Survey","created":"2021-04-30","cited_by_count":53,"area":null},{"id":"2207.14526","title":"Leveraging Explanations in Interactive Machine Learning: An Overview","created":"2022-07-29","cited_by_count":53,"area":null},{"id":"2205.15769","title":"Concept-level Debugging of Part-Prototype Networks","created":"2022-05-31","cited_by_count":52,"area":null},{"id":"2203.08008","title":"Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement","created":"2022-03-15","cited_by_count":48,"area":null},{"id":"2104.02297","title":"Shapley Explanation Networks","created":"2021-04-06","cited_by_count":41,"area":null},{"id":"2312.14223","title":"Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generation","created":"2023-12-21","cited_by_count":41,"area":null},{"id":"2106.02112","title":"Finding and Fixing Spurious Patterns with Explanations","created":"2021-06-03","cited_by_count":38,"area":null},{"id":"2212.03954","title":"Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning","created":"2022-12-07","cited_by_count":36,"area":null},{"id":"2111.07668","title":"Fast Axiomatic Attribution for Neural Networks","created":"2021-11-15","cited_by_count":35,"area":null},{"id":"2210.09520","title":"Using Language to Extend to Unseen Domains","created":"2022-10-18","cited_by_count":34,"area":null},{"id":"2107.09145","title":"Adaptive wavelet distillation from neural networks through interpretations","created":"2021-07-19","cited_by_count":32,"area":null},{"id":"2106.01127","title":"Towards Robust Classification Model by Counterfactual and Invariant Data Generation","created":"2021-06-02","cited_by_count":30,"area":null},{"id":"2202.08926","title":"On Guiding Visual Attention with Language Specification","created":"2022-02-17","cited_by_count":30,"area":null},{"id":"2308.13453","title":"Learning to Intervene on Concept Bottlenecks","created":"2023-08-25","cited_by_count":29,"area":null},{"id":"2103.10415","title":"Refining Language Models with Compositional Explanations","created":"2021-03-18","cited_by_count":27,"area":null},{"id":"2303.00885","title":"Towards Trustable Skin Cancer Diagnosis via Rewriting Model's Decision","created":"2023-03-02","cited_by_count":27,"area":null},{"id":"2112.00071","title":"What to Learn, and How: Toward Effective Learning from Rationales","created":"2021-11-30","cited_by_count":25,"area":null},{"id":"2111.04927","title":"Self-Interpretable Model with TransformationEquivariant Interpretation","created":"2021-11-09","cited_by_count":21,"area":null},{"id":"2208.12232","title":"A survey, review, and future trends of skin lesion segmentation and classification","created":"2022-08-25","cited_by_count":21,"area":null},{"id":"2308.09437","title":"From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Space","created":"2023-08-18","cited_by_count":20,"area":"safety"},{"id":"2110.00527","title":"Consistent Explanations by Contrastive Learning","created":"2021-10-01","cited_by_count":18,"area":null},{"id":"2303.12641","title":"Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models","created":"2023-03-22","cited_by_count":17,"area":null},{"id":"2309.08395","title":"Learning by Self-Explaining","created":"2023-09-15","cited_by_count":17,"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":"2105.10172","title":"Explainable Machine Learning with Prior Knowledge: An Overview","created":"2021-05-21","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":"2204.08892","title":"A survey on improving NLP models with human explanations","created":"2022-04-19","cited_by_count":15,"area":null},{"id":"2212.06925","title":"On the Relationship Between Explanation and Prediction: A Causal View","created":"2022-12-13","cited_by_count":14,"area":null},{"id":"2303.09660","title":"Explainable GeoAI: Can saliency maps help interpret artificial intelligence's learning process? An empirical study on natural feature detection","created":"2023-03-16","cited_by_count":14,"area":null},{"id":"2303.16390","title":"Are Data-driven Explanations Robust against Out-of-distribution Data?","created":"2023-03-29","cited_by_count":14,"area":null},{"id":"2310.01011","title":"Towards Fixing Clever-Hans Predictors with Counterfactual Knowledge Distillation","created":"2023-10-02","cited_by_count":14,"area":"distill"},{"id":"2407.14412","title":"DEAL: Disentangle and Localize Concept-level Explanations for VLMs","created":"2024-07-19","cited_by_count":14,"area":"mllm"},{"id":"2405.10729","title":"Contestable AI needs Computational Argumentation","created":"2024-05-17","cited_by_count":13,"area":null},{"id":"2307.10404","title":"Interpreting and Correcting Medical Image Classification with PIP-Net","created":"2023-07-19","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":"2111.12490","title":"Matching Learned Causal Effects of Neural Networks with Domain Priors","created":"2021-11-24","cited_by_count":10,"area":null},{"id":"2212.00017","title":"Knowledge-augmented Deep Learning and Its Applications: A Survey","created":"2022-11-30","cited_by_count":10,"area":null},{"id":"2311.15303","title":"Concept Distillation: Leveraging Human-Centered Explanations for Model Improvement","created":"2023-11-26","cited_by_count":10,"area":null},{"id":"2106.07787","title":"Tracing Back Music Emotion Predictions to Sound Sources and Intuitive Perceptual Qualities","created":"2021-06-14","cited_by_count":9,"area":null},{"id":"2304.05727","title":"Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks","created":"2023-04-12","cited_by_count":9,"area":null},{"id":"2308.00473","title":"Is Last Layer Re-Training Truly Sufficient for Robustness to Spurious Correlations?","created":"2023-08-01","cited_by_count":9,"area":null},{"id":"2407.14974","title":"Out of Spuriousity: Improving Robustness to Spurious Correlations without Group Annotations","created":"2024-07-20","cited_by_count":9,"area":null},{"id":"2410.10308","title":"LG-CAV: Train Any Concept Activation Vector with Language Guidance","created":"2024-10-14","cited_by_count":9,"area":"mllm"},{"id":"2210.16978","title":"XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models","created":"2022-10-30","cited_by_count":8,"area":null},{"id":"2302.05752","title":"Informing clinical assessment by contextualizing post-hoc explanations of risk prediction models in type-2 diabetes","created":"2023-02-11","cited_by_count":8,"area":null},{"id":"2303.14496","title":"Learning with Explanation Constraints","created":"2023-03-25","cited_by_count":8,"area":null},{"id":"2311.07286","title":"Explaining black boxes with a SMILE: Statistical Model-agnostic Interpretability with Local Explanations","created":"2023-11-13","cited_by_count":8,"area":null},{"id":"2312.04712","title":"Error Discovery by Clustering Influence Embeddings","created":"2023-12-07","cited_by_count":8,"area":null},{"id":"2402.06434","title":"Where is the Truth? The Risk of Getting Confounded in a Continual World","created":"2024-02-09","cited_by_count":8,"area":null},{"id":"2402.13410","title":"Bayesian Neural Networks with Domain Knowledge Priors","created":"2024-02-20","cited_by_count":8,"area":null},{"id":"2407.11771","title":"XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approach","created":"2024-07-16","cited_by_count":8,"area":null},{"id":"2203.03668","title":"A Typology for Exploring the Mitigation of Shortcut Behavior","created":"2022-03-04","cited_by_count":7,"area":null},{"id":"2209.03745","title":"Prior Knowledge-Guided Attention in Self-Supervised Vision Transformers","created":"2022-09-07","cited_by_count":7,"area":null},{"id":"2211.03041","title":"Calibration Meets Explanation: A Simple and Effective Approach for Model Confidence Estimates","created":"2022-11-06","cited_by_count":7,"area":null},{"id":"2103.06179","title":"Towards Learning an Unbiased Classifier from Biased Data via Conditional Adversarial Debiasing","created":"2021-03-10","cited_by_count":6,"area":null},{"id":"2205.12542","title":"ER-Test: Evaluating Explanation Regularization Methods for Language Models","created":"2022-05-25","cited_by_count":6,"area":null},{"id":"2302.02016","title":"Improving Interpretability via Explicit Word Interaction Graph Layer","created":"2023-02-03","cited_by_count":6,"area":null},{"id":"2303.13299","title":"Reckoning with the Disagreement Problem: Explanation Consensus as a Training Objective","created":"2023-03-23","cited_by_count":6,"area":null},{"id":"2401.06462","title":"AttributionScanner: A Visual Analytics System for Model Validation with Metadata-Free Slice Finding","created":"2024-01-12","cited_by_count":6,"area":null},{"id":"2405.13474","title":"Why do explanations fail? A typology and discussion on failures in XAI","created":"2024-05-22","cited_by_count":6,"area":null},{"id":"2202.09792","title":"Hierarchical Interpretation of Neural Text Classification","created":"2022-02-20","cited_by_count":5,"area":null},{"id":"2209.09975","title":"Power of Explanations: Towards automatic debiasing in hate speech detection","created":"2022-09-07","cited_by_count":5,"area":null},{"id":"2404.03098","title":"Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationales","created":"2024-04-03","cited_by_count":5,"area":null},{"id":"2404.09601","title":"Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression","created":"2024-04-15","cited_by_count":5,"area":null},{"id":"2407.05594","title":"SLIM: Spuriousness Mitigation with Minimal Human Annotations","created":"2024-07-08","cited_by_count":5,"area":null},{"id":"2103.13455","title":"Matched sample selection with GANs for mitigating attribute confounding","created":"2021-03-24","cited_by_count":4,"area":null},{"id":"2108.10131","title":"Improving the trustworthiness of image classification models by utilizing bounding-box annotations","created":"2021-08-15","cited_by_count":4,"area":null},{"id":"2304.09835","title":"An XAI framework for robust and transparent data-driven wind turbine power curve models","created":"2023-04-19","cited_by_count":4,"area":null},{"id":"2310.07882","title":"The Thousand Faces of Explainable AI Along the Machine Learning Life Cycle: Industrial Reality and Current State of Research","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2310.14418","title":"REFER: An End-to-end Rationale Extraction Framework for Explanation Regularization","created":"2023-10-22","cited_by_count":4,"area":null},{"id":"2312.17591","title":"Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training","created":"2023-12-29","cited_by_count":4,"area":null},{"id":"2403.07078","title":"Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning","created":"2024-03-11","cited_by_count":4,"area":null},{"id":"2203.12536","title":"Dynamically Refined Regularization for Improving Cross-corpora Hate Speech Detection","created":"2022-03-23","cited_by_count":3,"area":null},{"id":"2303.13918","title":"Removing confounding information from fetal ultrasound images","created":"2023-03-24","cited_by_count":3,"area":null},{"id":"2307.01473","title":"Mitigating Bias: Enhancing Image Classification by Improving Model Explanations","created":"2023-07-04","cited_by_count":3,"area":null},{"id":"2311.12813","title":"Targeted Activation Penalties Help CNNs Ignore Spurious Signals","created":"2023-09-22","cited_by_count":3,"area":null},{"id":"2505.10231","title":"On the Interplay of Human-AI Alignment,Fairness, and Performance Trade-offs in Medical Imaging","created":"2025-05-15","cited_by_count":3,"area":null},{"id":"2603.15656","title":"Attribution-Guided Model Rectification of Unreliable Neural Network Behaviors","created":"2026-03-08","cited_by_count":3,"area":null},{"id":"2202.00391","title":"Right for the Right Latent Factors: Debiasing Generative Models via Disentanglement","created":"2022-02-01","cited_by_count":2,"area":null},{"id":"2303.06419","title":"Use Perturbations when Learning from Explanations","created":"2023-03-11","cited_by_count":2,"area":null},{"id":"2303.13850","title":"Towards Learning and Explaining Indirect Causal Effects in Neural Networks","created":"2023-03-24","cited_by_count":2,"area":null},{"id":"2304.03838","title":"Improving Identity-Robustness for Face Models","created":"2023-04-07","cited_by_count":2,"area":null},{"id":"2304.07136","title":"One Explanation Does Not Fit XIL","created":"2023-04-14","cited_by_count":2,"area":null},{"id":"2312.02186","title":"Identifying Spurious Correlations using Counterfactual Alignment","created":"2023-12-01","cited_by_count":2,"area":null},{"id":"2403.06087","title":"Learning the irreversible progression trajectory of Alzheimer's disease","created":"2024-03-10","cited_by_count":2,"area":null},{"id":"2501.13818","title":"Ensuring Medical AI Safety: Interpretability-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data","created":"2025-01-23","cited_by_count":2,"area":null},{"id":"2502.14572","title":"Factor Graph-based Interpretable Neural Networks","created":"2025-02-20","cited_by_count":2,"area":null},{"id":"2503.05424","title":"Locally Explaining Prediction Behavior via Gradual Interventions and Measuring Property Gradients","created":"2025-03-07","cited_by_count":2,"area":null},{"id":"2504.15664","title":"An XAI-based Analysis of Shortcut Learning in Neural Networks","created":"2025-04-22","cited_by_count":2,"area":null},{"id":"2508.07636","title":"Attribution Explanations for Deep Neural Networks: A Theoretical Perspective","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2509.21247","title":"Learning to Look: Cognitive Attention Alignment with Vision-Language Models","created":"2025-09-25","cited_by_count":2,"area":"mllm"},{"id":"2605.02167","title":"Manifold-Aligned Guided Integrated Gradients for Reliable Feature Attribution","created":"2026-05-04","cited_by_count":2,"area":null}],"next_cursor":"100"}