{"total":39,"rows":[{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2207.00813","title":"Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysis","created":"2022-06-30","cited_by_count":59,"area":null},{"id":"2201.12114","title":"Rethinking Attention-Model Explainability through Faithfulness Violation Test","created":"2022-01-28","cited_by_count":43,"area":null},{"id":"2312.12141","title":"Neuron-Level Knowledge Attribution in Large Language Models","created":"2023-12-19","cited_by_count":37,"area":null},{"id":"2103.11072","title":"Local Interpretations for Explainable Natural Language Processing: A Survey","created":"2021-03-20","cited_by_count":31,"area":null},{"id":"2210.16966","title":"Interpretable Geometric Deep Learning via Learnable Randomness Injection","created":"2022-10-30","cited_by_count":27,"area":null},{"id":"2407.13934","title":"Towards Trustworthy AI: A Review of Ethical and Robust Large Language Models","created":"2024-06-01","cited_by_count":22,"area":null},{"id":"2405.02318","title":"Autoformalizing Natural Language to First-Order Logic: A Case Study in Logical Fallacy Detection","created":"2024-04-18","cited_by_count":18,"area":null},{"id":"2501.15638","title":"A Comprehensive Survey on Self-Interpretable Neural Networks","created":"2025-01-26","cited_by_count":18,"area":null},{"id":"2211.00582","title":"ClassActionPrediction: A Challenging Benchmark for Legal Judgment Prediction of Class Action Cases in the US","created":"2022-11-01","cited_by_count":17,"area":null},{"id":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2310.10318","title":"Interpreting and Exploiting Functional Specialization in Multi-Head Attention under Multi-task Learning","created":"2023-10-16","cited_by_count":9,"area":null},{"id":"2404.18570","title":"Analyzing Semantic Change through Lexical Replacements","created":"2024-04-29","cited_by_count":7,"area":null},{"id":"2503.09535","title":"Evaluating Visual Explanations of Attention Maps for Transformer-based Medical Imaging","created":"2025-03-12","cited_by_count":7,"area":null},{"id":"2402.08479","title":"Plausible Extractive Rationalization through Semi-Supervised Entailment Signal","created":"2024-02-13","cited_by_count":6,"area":null},{"id":"2505.06032","title":"Short-circuiting Shortcuts: Mechanistic Investigation of Shortcuts in Text Classification","created":"2025-05-09","cited_by_count":5,"area":null},{"id":"2210.02719","title":"Continuous Diagnosis and Prognosis by Controlling the Update Process of Deep Neural Networks","created":"2022-10-06","cited_by_count":4,"area":null},{"id":"2212.03396","title":"Learning to Select Prototypical Parts for Interpretable Sequential Data Modeling","created":"2022-12-07","cited_by_count":4,"area":null},{"id":"2201.05279","title":"Manifoldron: Direct Space Partition via Manifold Discovery","created":"2022-01-14","cited_by_count":2,"area":null},{"id":"2308.01621","title":"A Novel Convolutional Neural Network Architecture with a Continuous Symmetry","created":"2023-08-03","cited_by_count":2,"area":null},{"id":"2309.03631","title":"Insights Into the Inner Workings of Transformer Models for Protein Function Prediction","created":"2023-09-07","cited_by_count":2,"area":null},{"id":"2404.00140","title":"Does Faithfulness Conflict with Plausibility? An Empirical Study in Explainable AI across NLP Tasks","created":"2024-03-29","cited_by_count":2,"area":null},{"id":"2405.13972","title":"Infinite-Dimensional Feature Interaction","created":"2024-05-22","cited_by_count":2,"area":null},{"id":"2506.07871","title":"Can Hessian-Based Insights Support Fault Diagnosis in Attention-based Models?","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2310.06654","title":"Evaluating Explanation Methods for Vision-and-Language Navigation","created":"2023-10-10","cited_by_count":1,"area":null},{"id":"2405.00577","title":"Discovering robust biomarkers of psychiatric disorders from resting-state functional MRI via graph neural networks: A systematic review","created":"2024-05-01","cited_by_count":1,"area":null},{"id":"2407.00849","title":"Towards Understanding Sensitive and Decisive Patterns in Explainable AI: A Case Study of Model Interpretation in Geometric Deep Learning","created":"2024-06-30","cited_by_count":1,"area":null},{"id":"2501.12775","title":"Regularization, Semi-supervision, and Supervision for a Plausible Attention-Based Explanation","created":"2025-01-22","cited_by_count":1,"area":null},{"id":"2210.08097","title":"TestAug: A Framework for Augmenting Capability-based NLP Tests","created":"2022-10-14","cited_by_count":0,"area":null},{"id":"2312.09513","title":"CGS-Mask: Making Time Series Predictions Intuitive for All","created":"2023-12-15","cited_by_count":0,"area":null},{"id":"2410.08829","title":"Exploiting Latent Linearity in LLMs Improves Explainable Molecular Representation Learning","created":"2024-10-11","cited_by_count":0,"area":null},{"id":"2504.03703","title":"Hierarchical Attention Network for Interpretable ECG-based Heart Disease Classification","created":"2025-03-25","cited_by_count":0,"area":null},{"id":"2507.10596","title":"PLEX: Perturbation-free Local Explanations for LLM-Based Text Classification","created":"2025-07-12","cited_by_count":0,"area":null},{"id":"2508.04427","title":"Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Models","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2509.11513","title":"Unsupervised Candidate Ranking for Lexical Substitution via Holistic Sentence Semantics","created":"2025-09-15","cited_by_count":0,"area":null},{"id":"2510.00517","title":"Understanding Sensitivity of Differential Attention through the Lens of Adversarial Robustness","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2510.09350","title":"Deep Learning to Identify the Spatio-Temporal Cascading Effects of Train Delays in a High-Density Network","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2510.10803","title":"PruneGCRN: Minimizing and explaining spatio-temporal problems through node pruning","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2601.09156","title":"KTCF: Actionable Recourse in Knowledge Tracing via Counterfactual Explanations for Education","created":"2026-01-14","cited_by_count":0,"area":null}],"next_cursor":null}