{"total":59,"rows":[{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2310.07521","title":"Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity","created":"2023-10-11","cited_by_count":206,"area":null},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2308.13198","title":"Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neurons","created":"2023-08-25","cited_by_count":56,"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":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2306.06123","title":"Adversarial attacks and defenses in explainable artificial intelligence: A survey","created":"2023-06-06","cited_by_count":48,"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":"2404.09554","title":"Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda","created":"2024-04-15","cited_by_count":22,"area":null},{"id":"2405.09800","title":"Manifold Integrated Gradients: Riemannian Geometry for Feature Attribution","created":"2024-05-16","cited_by_count":21,"area":null},{"id":"2410.07054","title":"Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing","created":"2024-10-09","cited_by_count":18,"area":null},{"id":"2205.12423","title":"Deletion and Insertion Tests in Regression Models","created":"2022-05-25","cited_by_count":14,"area":null},{"id":"2307.05902","title":"Stability Guarantees for Feature Attributions with Multiplicative Smoothing","created":"2023-07-12","cited_by_count":14,"area":null},{"id":"2405.14117","title":"Knowledge Localization: Mission Not Accomplished? Enter Query Localization!","created":"2024-05-23","cited_by_count":13,"area":null},{"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":"2204.05376","title":"medXGAN: Visual Explanations for Medical Classifiers through a Generative Latent Space","created":"2022-04-11","cited_by_count":10,"area":null},{"id":"2401.04374","title":"Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective","created":"2024-01-09","cited_by_count":9,"area":null},{"id":"2502.10927","title":"The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training","created":"2025-02-15","cited_by_count":9,"area":null},{"id":"2302.11107","title":"Non-Uniform Interpolation in Integrated Gradients for Low-Latency Explainable-AI","created":"2023-02-22","cited_by_count":5,"area":null},{"id":"2306.13753","title":"Four Axiomatic Characterizations of the Integrated Gradients Attribution Method","created":"2023-06-23","cited_by_count":5,"area":null},{"id":"2407.19308","title":"Comprehensive Attribution: Inherently Explainable Vision Model with Feature Detector","created":"2024-07-27","cited_by_count":5,"area":null},{"id":"2409.12952","title":"The Gaussian Discriminant Variational Autoencoder (GdVAE): A Self-Explainable Model with Counterfactual Explanations","created":"2024-09-19","cited_by_count":5,"area":null},{"id":"2502.20408","title":"Brain-Inspired Exploration of Functional Networks and Key Neurons in Large Language Models","created":"2025-02-13","cited_by_count":5,"area":null},{"id":"2301.13445","title":"A Survey of Explainable AI in Deep Visual Modeling: Methods and Metrics","created":"2023-01-31","cited_by_count":4,"area":null},{"id":"2402.18863","title":"Probabilistic Lipschitzness and the Stable Rank for Comparing Explanation Models","created":"2024-02-29","cited_by_count":4,"area":null},{"id":"2406.18334","title":"Efficient and Accurate Explanation Estimation with Distribution Compression","created":"2024-06-26","cited_by_count":4,"area":null},{"id":"2208.06096","title":"Comparing Baseline Shapley and Integrated Gradients for Local Explanation: Some Additional Insights","created":"2022-08-12","cited_by_count":3,"area":null},{"id":"2211.08425","title":"A Rigorous Study Of The Deep Taylor Decomposition","created":"2022-11-14","cited_by_count":3,"area":null},{"id":"2305.14395","title":"Towards credible visual model interpretation with path attribution","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2402.13731","title":"Cracking Factual Knowledge: A Comprehensive Analysis of Degenerate Knowledge Neurons in Large Language Models","created":"2024-02-21","cited_by_count":3,"area":null},{"id":"2408.11252","title":"Counterfactuals As a Means for Evaluating Faithfulness of Attribution Methods in Autoregressive Language Models","created":"2024-08-21","cited_by_count":3,"area":null},{"id":"2503.08240","title":"Tangentially Aligned Integrated Gradients for User-Friendly Explanations","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2305.03100","title":"Distributing Synergy Functions: Unifying Game-Theoretic Interaction Methods for Machine-Learning Explainability","created":"2023-05-04","cited_by_count":2,"area":null},{"id":"2403.15603","title":"Forward Learning for Gradient-based Black-box Saliency Map Generation","created":"2024-03-22","cited_by_count":2,"area":null},{"id":"2412.18053","title":"Neuron Empirical Gradient: Discovering and Quantifying Neurons Global Linear Controllability","created":"2024-12-24","cited_by_count":2,"area":null},{"id":"2503.00892","title":"Riemannian Integrated Gradients: A Geometric View of Explainable AI","created":"2025-03-02","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":"2308.08949","title":"A Dual-Perspective Approach to Evaluating Feature Attribution Methods","created":"2023-08-17","cited_by_count":1,"area":null},{"id":"2309.13246","title":"Can I Trust the Explanations? Investigating Explainable Machine Learning Methods for Monotonic Models","created":"2023-09-23","cited_by_count":1,"area":null},{"id":"2403.07072","title":"Explainable Learning with Gaussian Processes","created":"2024-03-11","cited_by_count":1,"area":null},{"id":"2404.13910","title":"Integrated Gradient Correlation: a Dataset-wise Attribution Method","created":"2024-04-22","cited_by_count":1,"area":null},{"id":"2405.10552","title":"Data Science Principles for Interpretable and Explainable AI","created":"2024-05-17","cited_by_count":1,"area":null},{"id":"2406.13292","title":"An interpretable generative multimodal neuroimaging-genomics framework for decoding Alzheimer's disease","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2407.08953","title":"Attribution Methods in Asset Pricing: Do They Account for Risk?","created":"2024-07-12","cited_by_count":1,"area":null},{"id":"2412.19897","title":"Surrogate Modeling for Explainable Predictive Time Series Corrections","created":"2024-12-27","cited_by_count":1,"area":null},{"id":"2503.19813","title":"Guidelines For The Choice Of The Baseline in XAI Attribution Methods","created":"2025-03-25","cited_by_count":1,"area":null},{"id":"2605.22243","title":"Explainable AI for Data-Driven Design of High-Dimensional Predictive Studies","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2311.06192","title":"Greedy PIG: Adaptive Integrated Gradients","created":"2023-11-10","cited_by_count":0,"area":null},{"id":"2405.16259","title":"Front-propagation Algorithm: Explainable AI Technique for Extracting Linear Function Approximations from Neural Networks","created":"2024-05-25","cited_by_count":0,"area":null},{"id":"2409.16865","title":"Linking in Style: Understanding learned features in deep learning models","created":"2024-09-25","cited_by_count":0,"area":null},{"id":"2503.12683","title":"Algebraic Adversarial Attacks on Explainability Models","created":"2025-03-16","cited_by_count":0,"area":null},{"id":"2506.06653","title":"Explaining Risks: Axiomatic Risk Attributions for Financial Models","created":"2025-06-07","cited_by_count":0,"area":null},{"id":"2508.14482","title":"On the notion of missingness for path attribution explainability methods in medical settings: Guiding the selection of medically meaningful baselines","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2509.07648","title":"Graph-based Integrated Gradients for Explaining Graph Neural Networks","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2602.11841","title":"Improving Neural Retrieval with Attribution-Guided Query Rewriting","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.16067","title":"Attribution Upsampling should Redistribute, Not Interpolate","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2605.05480","title":"GRALIS: Fusing Coalition and Gradient Attribution with Closed-Form Conservation Error and Finite-Sample Guarantees","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2606.03885","title":"Attribution via Distributional Paths for Information Revelation","created":"2026-06-02","cited_by_count":0,"area":null}],"next_cursor":null}