{"total":77,"rows":[{"id":"2106.02997","title":"Causal Abstractions of Neural Networks","created":"2021-06-06","cited_by_count":422,"area":null},{"id":"2301.04709","title":"Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability","created":"2023-01-11","cited_by_count":205,"area":"mechinterp"},{"id":"2107.10912","title":"Explainable artificial intelligence (XAI) in deep learning-based medical image analysis","created":"2021-07-22","cited_by_count":147,"area":null},{"id":"2104.06643","title":"Generative Causal Explanations for Graph Neural Networks","created":"2021-04-14","cited_by_count":124,"area":null},{"id":"2112.00826","title":"Inducing Causal Structure for Interpretable Neural Networks","created":"2021-12-01","cited_by_count":110,"area":null},{"id":"2101.02032","title":"Socially Responsible AI Algorithms: Issues, Purposes, and Challenges","created":"2021-01-01","cited_by_count":56,"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":"2204.09274","title":"Causality-based Neural Network Repair","created":"2022-04-20","cited_by_count":47,"area":"safety"},{"id":"2201.09119","title":"A Causal Lens for Controllable Text Generation","created":"2022-01-22","cited_by_count":45,"area":null},{"id":"2309.10312","title":"Rigorously Assessing Natural Language Explanations of Neurons","created":"2023-09-19","cited_by_count":45,"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":"2204.11028","title":"Reinforced Causal Explainer for Graph Neural Networks","created":"2022-04-23","cited_by_count":34,"area":null},{"id":"2307.16851","title":"Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives","created":"2023-07-31","cited_by_count":30,"area":"alignment"},{"id":"2405.16507","title":"Causal Concept Graph Models: Beyond Causal Opacity in Deep Learning","created":"2024-05-26","cited_by_count":29,"area":null},{"id":"2302.02876","title":"Variational Information Pursuit for Interpretable Predictions","created":"2023-02-06","cited_by_count":25,"area":null},{"id":"2112.05746","title":"On Causally Disentangled Representations","created":"2021-12-10","cited_by_count":22,"area":null},{"id":"2106.00925","title":"Contrastive ACE: Domain Generalization Through Alignment of Causal Mechanisms","created":"2021-06-02","cited_by_count":20,"area":null},{"id":"2209.07190","title":"Adaptive Fairness Improvement Based on Causality Analysis","created":"2022-09-15","cited_by_count":17,"area":null},{"id":"2305.14582","title":"Interpretation of Time-Series Deep Models: A Survey","created":"2023-05-23","cited_by_count":15,"area":null},{"id":"2504.12691","title":"Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations","created":"2025-04-17","cited_by_count":15,"area":null},{"id":"2602.07918","title":"CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution","created":"2026-02-08","cited_by_count":14,"area":"agents"},{"id":"2410.16638","title":"LLMScan: Causal Scan for LLM Misbehavior Detection","created":"2024-10-22","cited_by_count":13,"area":null},{"id":"2212.07056","title":"On the Probability of Necessity and Sufficiency of Explaining Graph Neural Networks: A Lower Bound Optimization Approach","created":"2022-12-14","cited_by_count":11,"area":null},{"id":"2312.07876","title":"Causality Analysis for Evaluating the Security of Large Language Models","created":"2023-12-13","cited_by_count":11,"area":"alignment"},{"id":"2105.10719","title":"Can We Faithfully Represent Masked States to Compute Shapley Values on a DNN?","created":"2021-05-22","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":"2506.05451","title":"Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety","created":"2025-06-05","cited_by_count":10,"area":"safety"},{"id":"2312.16113","title":"Task-Driven Causal Feature Distillation: Towards Trustworthy Risk Prediction","created":"2023-12-20","cited_by_count":9,"area":"distill"},{"id":"2104.12759","title":"Instance-wise Causal Feature Selection for Model Interpretation","created":"2021-04-26","cited_by_count":8,"area":null},{"id":"2109.06404","title":"Detecting Multi-Sensor Fusion Errors in Advanced Driver-Assistance Systems","created":"2021-09-14","cited_by_count":8,"area":null},{"id":"2305.08950","title":"Causal Analysis for Robust Interpretability of Neural Networks","created":"2023-05-15","cited_by_count":8,"area":null},{"id":"2104.12278","title":"Causal Learning for Socially Responsible AI","created":"2021-04-25","cited_by_count":7,"area":null},{"id":"2208.08982","title":"Quality issues in Machine Learning Software Systems","created":"2022-08-18","cited_by_count":7,"area":null},{"id":"2104.09073","title":"Improving Attribution Methods by Learning Submodular Functions","created":"2021-04-19","cited_by_count":5,"area":null},{"id":"2110.11929","title":"Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?","created":"2021-10-22","cited_by_count":5,"area":null},{"id":"2208.13472","title":"Supporting Medical Relation Extraction via Causality-Pruned Semantic Dependency Forest","created":"2022-08-29","cited_by_count":5,"area":null},{"id":"2211.04780","title":"On the Robustness of Explanations of Deep Neural Network Models: A Survey","created":"2022-11-09","cited_by_count":5,"area":null},{"id":"2303.00244","title":"SUNY: A Visual Interpretation Framework for Convolutional Neural Networks from a Necessary and Sufficient Perspective","created":"2023-03-01","cited_by_count":5,"area":null},{"id":"2312.05356","title":"Neuron Patching: Semantic-based Neuron-level Language Model Repair for Code Generation","created":"2023-12-08","cited_by_count":5,"area":null},{"id":"2401.08534","title":"DiConStruct: Causal Concept-based Explanations through Black-Box Distillation","created":"2024-01-16","cited_by_count":5,"area":"distill"},{"id":"2308.04177","title":"How Generalizable are Deepfake Image Detectors? An Empirical Study","created":"2023-08-08","cited_by_count":3,"area":null},{"id":"2312.16815","title":"Emergence and Causality in Complex Systems: A Survey on Causal Emergence and Related Quantitative Studies","created":"2023-12-28","cited_by_count":3,"area":null},{"id":"2512.19297","title":"Causal-Guided Detoxify Backdoor Attack of Open-Weight LoRA Models","created":"2025-12-22","cited_by_count":3,"area":null},{"id":"2106.00266","title":"Did I do that? Blame as a means to identify controlled effects in reinforcement learning","created":"2021-06-01","cited_by_count":2,"area":null},{"id":"2201.01155","title":"DeepVisualInsight: Time-Travelling Visualization for Spatio-Temporal Causality of Deep Classification Training","created":"2021-12-31","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":"2311.04778","title":"On the Multiple Roles of Ontologies in Explainable AI","created":"2023-11-08","cited_by_count":2,"area":null},{"id":"2402.02696","title":"Causal Feature Selection for Responsible Machine Learning","created":"2024-02-05","cited_by_count":2,"area":null},{"id":"2503.12899","title":"A Semantic-based Optimization Approach for Repairing LLMs: Case Study on Code Generation","created":"2025-03-17","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":"2603.13652","title":"Causal Attribution via Activation Patching","created":"2026-03-13","cited_by_count":2,"area":"mechinterp"},{"id":"2206.11529","title":"Explanatory causal effects for model agnostic explanations","created":"2022-06-23","cited_by_count":1,"area":null},{"id":"2210.13507","title":"Causal Explanation for Reinforcement Learning: Quantifying State and Temporal Importance","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2212.14106","title":"Provable Robust Saliency-based Explanations","created":"2022-12-28","cited_by_count":1,"area":null},{"id":"2303.01302","title":"Reasoning-Based Software Testing","created":"2023-03-02","cited_by_count":1,"area":null},{"id":"2312.12878","title":"Rule-Extraction Methods From Feedforward Neural Networks: A Systematic Literature Review","created":"2023-12-20","cited_by_count":1,"area":null},{"id":"2405.20672","title":"Investigating and unmasking feature-level vulnerabilities of CNNs to adversarial perturbations","created":"2024-05-31","cited_by_count":1,"area":null},{"id":"2410.13488","title":"Seeing Through VisualBERT: A Causal Adventure on Memetic Landscapes","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2410.15648","title":"Linking Model Intervention to Causal Interpretation in Model Explanation","created":"2024-10-21","cited_by_count":1,"area":null},{"id":"2512.06814","title":"CAuSE: Decoding Multimodal Classifiers using Faithful Natural Language Explanation","created":"2025-12-07","cited_by_count":1,"area":null},{"id":"2608.12921","title":"Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference","created":"2026-08-13","cited_by_count":1,"area":"agents"},{"id":"2101.04047","title":"Learning to Ignore: Fair and Task Independent Representations","created":"2021-01-11","cited_by_count":0,"area":null},{"id":"2106.05842","title":"Causality in Neural Networks -- An Extended Abstract","created":"2021-06-03","cited_by_count":0,"area":null},{"id":"2201.11783","title":"Boosting Exploration in Multi-Task Reinforcement Learning using Adversarial Networks","created":"2022-01-27","cited_by_count":0,"area":null},{"id":"2206.07194","title":"Machines Explaining Linear Programs","created":"2022-06-14","cited_by_count":0,"area":null},{"id":"2306.15007","title":"Quality Issues in Machine Learning Software Systems","created":"2023-06-26","cited_by_count":0,"area":null},{"id":"2307.04024","title":"Robust Ranking Explanations","created":"2023-07-08","cited_by_count":0,"area":null},{"id":"2505.09660","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","created":"2025-05-14","cited_by_count":0,"area":null},{"id":"2505.21552","title":"Understanding the learned look-ahead behavior of chess neural networks","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2509.16268","title":"Digging Into the Internal: Causality-Based Analysis of LLM Function Calling","created":"2025-09-18","cited_by_count":0,"area":"agents"},{"id":"2509.18568","title":"Explainable Graph Neural Networks: Understanding Brain Connectivity and Biomarkers in Dementia","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2511.13021","title":"PragWorld: A Benchmark Evaluating LLMs' Local World Model under Minimal Linguistic Alterations and Conversational Dynamics","created":"2025-11-17","cited_by_count":0,"area":"wm"},{"id":"2512.21746","title":"A Model of Causal Explanation on Neural Networks for Tabular Data","created":"2025-12-25","cited_by_count":0,"area":null},{"id":"2603.28597","title":"Position: Explainable AI is Causality in Disguise","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.08890","title":"A Closer Look at the Application of Causal Inference in Graph Representation Learning","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2606.10877","title":"XtrAIn: Training-Guided Occlusion for Feature Attribution","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2608.12935","title":"Decomposition of Evidence, Contradiction, and Fragility in Perturbation Responses","created":"2026-08-13","cited_by_count":0,"area":null}],"next_cursor":null}