{"total":294,"rows":[{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737,"area":null},{"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":"2103.11790","title":"Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do","created":"2021-03-08","cited_by_count":178,"area":null},{"id":"2103.02023","title":"EnD: Entangling and Disentangling deep representations for bias correction","created":"2021-03-02","cited_by_count":105,"area":null},{"id":"2108.05233","title":"EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks","created":"2021-08-11","cited_by_count":92,"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":"2407.14499","title":"Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery","created":"2024-07-19","cited_by_count":91,"area":"mechinterp"},{"id":"2105.05612","title":"Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization","created":"2021-05-12","cited_by_count":83,"area":null},{"id":"2102.02201","title":"When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data","created":"2021-02-03","cited_by_count":75,"area":null},{"id":"2103.01378","title":"Contrastive Explanations for Model Interpretability","created":"2021-03-02","cited_by_count":75,"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":"2206.02349","title":"Invariant Grounding for Video Question Answering","created":"2022-06-06","cited_by_count":68,"area":null},{"id":"2305.19951","title":"Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts","created":"2023-05-31","cited_by_count":63,"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":"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":"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":"2203.08008","title":"Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement","created":"2022-03-15","cited_by_count":48,"area":null},{"id":"2402.04616","title":"Beyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge Distillation","created":"2024-02-07","cited_by_count":47,"area":"lr"},{"id":"2105.07878","title":"A Review on Explainability in Multimodal Deep Neural Nets","created":"2021-05-17","cited_by_count":46,"area":null},{"id":"2202.01034","title":"Diagnosing failures of fairness transfer across distribution shift in real-world medical settings","created":"2022-02-02","cited_by_count":45,"area":null},{"id":"2111.01564","title":"MultiplexNet: Towards Fully Satisfied Logical Constraints in Neural Networks","created":"2021-11-02","cited_by_count":44,"area":null},{"id":"2104.02297","title":"Shapley Explanation Networks","created":"2021-04-06","cited_by_count":41,"area":null},{"id":"2205.03295","title":"The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations","created":"2022-05-06","cited_by_count":41,"area":null},{"id":"2206.01161","title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","created":"2022-06-02","cited_by_count":41,"area":null},{"id":"2207.04153","title":"Probing Classifiers are Unreliable for Concept Removal and Detection","created":"2022-07-08","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":"2204.13074","title":"Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement","created":"2022-04-27","cited_by_count":37,"area":"lr"},{"id":"2112.03753","title":"Tell me why! Explanations support learning relational and causal structure","created":"2021-12-07","cited_by_count":36,"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":"2302.01242","title":"Neuro-Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept Rehearsal","created":"2023-02-02","cited_by_count":33,"area":null},{"id":"2303.05506","title":"TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization","created":"2023-03-09","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":"2101.04109","title":"Explain and Predict, and then Predict Again","created":"2021-01-11","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":"2110.03212","title":"Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates","created":"2021-10-07","cited_by_count":27,"area":null},{"id":"2112.14005","title":"Towards Relatable Explainable AI with the Perceptual Process","created":"2021-12-28","cited_by_count":27,"area":null},{"id":"2202.02838","title":"Aligning Eyes between Humans and Deep Neural Network through Interactive Attention Alignment","created":"2022-02-06","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":"2410.05495","title":"Self-rationalization improves LLM as a fine-grained judge","created":"2024-10-07","cited_by_count":27,"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":"2112.00071","title":"What to Learn, and How: Toward Effective Learning from Rationales","created":"2021-11-30","cited_by_count":25,"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":"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":"2112.02290","title":"Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representations","created":"2021-12-04","cited_by_count":24,"area":null},{"id":"2110.01013","title":"Counterfactual Samples Synthesizing and Training for Robust Visual Question Answering","created":"2021-10-03","cited_by_count":22,"area":null},{"id":"2206.13413","title":"RES: A Robust Framework for Guiding Visual Explanation","created":"2022-06-27","cited_by_count":22,"area":null},{"id":"2207.12783","title":"Equivariant and Invariant Grounding for Video Question Answering","created":"2022-07-26","cited_by_count":22,"area":null},{"id":"2404.09554","title":"Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda","created":"2024-04-15","cited_by_count":22,"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":"2110.10470","title":"Interpreting Deep Learning Models in Natural Language Processing: A Review","created":"2021-10-20","cited_by_count":19,"area":null},{"id":"2101.07337","title":"Dissonance Between Human and Machine Understanding","created":"2021-01-18","cited_by_count":18,"area":null},{"id":"2110.00527","title":"Consistent Explanations by Contrastive Learning","created":"2021-10-01","cited_by_count":18,"area":null},{"id":"2111.03015","title":"Modeling Techniques for Machine Learning Fairness: A Survey","created":"2021-11-04","cited_by_count":17,"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":"2104.02768","title":"Robust Semantic Interpretability: Revisiting Concept Activation Vectors","created":"2021-04-06","cited_by_count":16,"area":null},{"id":"2108.13759","title":"Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience","created":"2021-08-31","cited_by_count":16,"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":"2305.04224","title":"Visual Causal Scene Refinement for Video Question Answering","created":"2023-05-07","cited_by_count":16,"area":null},{"id":"2101.09498","title":"Show or Suppress? Managing Input Uncertainty in Machine Learning Model Explanations","created":"2021-01-23","cited_by_count":15,"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":"2111.03740","title":"Toward Learning Human-aligned Cross-domain Robust Models by Countering Misaligned Features","created":"2021-11-05","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":"2402.03119","title":"Good Teachers Explain: Explanation-Enhanced Knowledge Distillation","created":"2024-02-05","cited_by_count":14,"area":"distill"},{"id":"2406.09949","title":"Neural Concept Binder","created":"2024-06-14","cited_by_count":14,"area":"lr"},{"id":"2201.11259","title":"Controlling Directions Orthogonal to a Classifier","created":"2022-01-27","cited_by_count":13,"area":null},{"id":"2306.15774","title":"Next Steps for Human-Centered Generative AI: A Technical Perspective","created":"2023-06-27","cited_by_count":13,"area":null},{"id":"2405.10729","title":"Contestable AI needs Computational Argumentation","created":"2024-05-17","cited_by_count":13,"area":null},{"id":"2206.11212","title":"VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives","created":"2022-06-22","cited_by_count":12,"area":"lr"},{"id":"2307.00928","title":"Learning Differentiable Logic Programs for Abstract Visual Reasoning","created":"2023-07-03","cited_by_count":12,"area":"lr"},{"id":"2308.05362","title":"FINER: Enhancing State-of-the-art Classifiers with Feature Attribution to Facilitate Security Analysis","created":"2023-08-10","cited_by_count":12,"area":null},{"id":"2311.17983","title":"Improving Interpretation Faithfulness for Vision Transformers","created":"2023-11-29","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":"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":"2112.10424","title":"Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction","created":"2021-12-20","cited_by_count":11,"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":"2408.07461","title":"Problem Solving Through Human-AI Preference-Based Cooperation","created":"2024-08-14","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":"2107.01943","title":"When and How to Fool Explainable Models (and Humans) with Adversarial Examples","created":"2021-07-05","cited_by_count":10,"area":null},{"id":"2109.12422","title":"Equality of opportunity in travel behavior prediction with deep neural networks and discrete choice models","created":"2021-09-25","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":"2201.05177","title":"Making a (Counterfactual) Difference One Rationale at a Time","created":"2022-01-13","cited_by_count":10,"area":null},{"id":"2207.03444","title":"Fairness and Bias in Robot Learning","created":"2022-07-07","cited_by_count":10,"area":null},{"id":"2210.14672","title":"Sparsity in Continuous-Depth Neural Networks","created":"2022-10-26","cited_by_count":10,"area":null},{"id":"2211.08285","title":"Identifying Spurious Correlations and Correcting them with an Explanation-based Learning","created":"2022-11-15","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":"2407.04370","title":"Regulating Model Reliance on Non-Robust Features by Smoothing Input Marginal Density","created":"2024-07-05","cited_by_count":10,"area":null},{"id":"2506.05035","title":"TIMING: Temporality-Aware Integrated Gradients for Time Series Explanation","created":"2025-06-05","cited_by_count":10,"area":null},{"id":"2102.01916","title":"Answer Questions with Right Image Regions: A Visual Attention Regularization Approach","created":"2021-02-03","cited_by_count":9,"area":null},{"id":"2103.15429","title":"Efficient Explanations from Empirical Explainers","created":"2021-03-29","cited_by_count":9,"area":null},{"id":"2303.17707","title":"Why is plausibility surprisingly problematic as an XAI criterion?","created":"2023-03-30","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":"2404.18655","title":"Revealing the Parametric Knowledge of Language Models: A Unified Framework for Attribution Methods","created":"2024-04-29","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":"2106.01809","title":"Exploring Distantly-Labeled Rationales in Neural Network Models","created":"2021-06-03","cited_by_count":8,"area":null},{"id":"2210.10332","title":"Revision Transformers: Instructing Language Models to Change their Values","created":"2022-10-19","cited_by_count":8,"area":null}],"next_cursor":"100"}