{"total":210,"rows":[{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691,"area":null},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001,"area":null},{"id":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712,"area":null},{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435,"area":null},{"id":"2106.02997","title":"Causal Abstractions of Neural Networks","created":"2021-06-06","cited_by_count":422,"area":null},{"id":"2310.15213","title":"Function Vectors in Large Language Models","created":"2023-10-23","cited_by_count":308,"area":null},{"id":"2303.02536","title":"Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations","created":"2023-03-05","cited_by_count":209,"area":null},{"id":"2304.05969","title":"Localizing Model Behavior with Path Patching","created":"2023-04-12","cited_by_count":195,"area":null},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156,"area":null},{"id":"2106.06087","title":"Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models","created":"2021-06-10","cited_by_count":131,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2108.08728","title":"Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification","created":"2021-08-19","cited_by_count":114,"area":null},{"id":"2112.00826","title":"Inducing Causal Structure for Interpretable Neural Networks","created":"2021-12-01","cited_by_count":110,"area":null},{"id":"2201.01490","title":"Debiased Learning from Naturally Imbalanced Pseudo-Labels","created":"2022-01-05","cited_by_count":85,"area":null},{"id":"2501.06346","title":"Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages","created":"2025-01-10","cited_by_count":59,"area":null},{"id":"2210.00035","title":"Neural Causal Models for Counterfactual Identification and Estimation","created":"2022-09-30","cited_by_count":57,"area":null},{"id":"2406.16254","title":"Confidence Regulation Neurons in Language Models","created":"2024-06-24","cited_by_count":57,"area":null},{"id":"2407.17817","title":"Demystifying Verbatim Memorization in Large Language Models","created":"2024-07-25","cited_by_count":56,"area":null},{"id":"2103.11972","title":"Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactuals","created":"2021-03-22","cited_by_count":55,"area":null},{"id":"2306.15764","title":"High Fidelity Image Counterfactuals with Probabilistic Causal Models","created":"2023-06-27","cited_by_count":53,"area":null},{"id":"2102.01685","title":"Agent Incentives: A Causal Perspective","created":"2021-02-02","cited_by_count":51,"area":null},{"id":"2408.13656","title":"Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic","created":"2024-08-24","cited_by_count":50,"area":null},{"id":"2409.01659","title":"Interpreting and Improving Large Language Models in Arithmetic Calculation","created":"2024-09-03","cited_by_count":45,"area":null},{"id":"2107.14202","title":"Human Trajectory Prediction via Counterfactual Analysis","created":"2021-07-29","cited_by_count":42,"area":null},{"id":"2204.00607","title":"From Statistical to Causal Learning","created":"2022-04-01","cited_by_count":40,"area":null},{"id":"2410.07819","title":"Uncovering Overfitting in Large Language Model Editing","created":"2024-10-10","cited_by_count":39,"area":null},{"id":"2105.09829","title":"Personalized Counterfactual Fairness in Recommendation","created":"2021-05-20","cited_by_count":38,"area":null},{"id":"2107.03190","title":"Nested Counterfactual Identification from Arbitrary Surrogate Experiments","created":"2021-07-07","cited_by_count":38,"area":null},{"id":"2207.05302","title":"Causal Conceptions of Fairness and their Consequences","created":"2022-07-12","cited_by_count":38,"area":null},{"id":"2403.18167","title":"Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations","created":"2024-03-27","cited_by_count":38,"area":null},{"id":"2108.13134","title":"Factual Consistency Evaluation for Text Summarization via Counterfactual Estimation","created":"2021-08-30","cited_by_count":37,"area":null},{"id":"2310.18362","title":"SoK: Memorization in General-Purpose Large Language Models","created":"2023-10-24","cited_by_count":37,"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":"2112.06837","title":"Sparse Interventions in Language Models with Differentiable Masking","created":"2021-12-13","cited_by_count":34,"area":null},{"id":"2310.19704","title":"A Survey on Knowledge Editing of Neural Networks","created":"2023-10-30","cited_by_count":34,"area":null},{"id":"2306.03428","title":"GaitGCI: Generative Counterfactual Intervention for Gait Recognition","created":"2023-06-06","cited_by_count":31,"area":null},{"id":"2403.19521","title":"Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models","created":"2024-03-28","cited_by_count":31,"area":null},{"id":"2409.14144","title":"Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis","created":"2024-09-21","cited_by_count":31,"area":null},{"id":"2104.02921","title":"Unsupervised Visual Attention and Invariance for Reinforcement Learning","created":"2021-04-07","cited_by_count":30,"area":null},{"id":"2201.13169","title":"Causal Explanations and XAI","created":"2022-01-31","cited_by_count":30,"area":null},{"id":"2305.14956","title":"Editing Common Sense in Transformers","created":"2023-05-24","cited_by_count":28,"area":null},{"id":"2405.01008","title":"On Mechanistic Knowledge Localization in Text-to-Image Generative Models","created":"2024-05-02","cited_by_count":28,"area":null},{"id":"2405.16821","title":"Perturbation-Restrained Sequential Model Editing","created":"2024-05-27","cited_by_count":28,"area":null},{"id":"2605.05115","title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","created":"2026-05-06","cited_by_count":26,"area":null},{"id":"2111.01026","title":"Introspective Distillation for Robust Question Answering","created":"2021-11-01","cited_by_count":25,"area":null},{"id":"2310.18913","title":"Debiasing Algorithm through Model Adaptation","created":"2023-10-29","cited_by_count":24,"area":null},{"id":"2404.05729","title":"Finding Visual Task Vectors","created":"2024-04-08","cited_by_count":24,"area":null},{"id":"2202.01300","title":"Causal Inference Through the Structural Causal Marginal Problem","created":"2022-02-02","cited_by_count":23,"area":null},{"id":"2407.04690","title":"Missed Causes and Ambiguous Effects: Counterfactuals Pose Challenges for Interpreting Neural Networks","created":"2024-07-05","cited_by_count":23,"area":null},{"id":"2204.10018","title":"Path-Specific Objectives for Safer Agent Incentives","created":"2022-04-21","cited_by_count":20,"area":null},{"id":"2403.09683","title":"Counterfactual Image Editing","created":"2024-02-07","cited_by_count":20,"area":null},{"id":"2112.02505","title":"Causal Distillation for Language Models","created":"2021-12-05","cited_by_count":19,"area":null},{"id":"2402.02872","title":"How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for Metric Learning","created":"2024-02-05","cited_by_count":18,"area":null},{"id":"2205.10095","title":"How to keep text private? A systematic review of deep learning methods for privacy-preserving natural language processing","created":"2022-05-20","cited_by_count":16,"area":null},{"id":"2206.06685","title":"Causal Discovery for Fairness","created":"2022-06-14","cited_by_count":16,"area":null},{"id":"2206.04551","title":"A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning","created":"2022-06-09","cited_by_count":15,"area":null},{"id":"2104.06400","title":"Mediators in Determining what Processing BERT Performs First","created":"2021-04-13","cited_by_count":14,"area":null},{"id":"2210.14328","title":"Causal Analysis of Syntactic Agreement Neurons in Multilingual Language Models","created":"2022-10-25","cited_by_count":14,"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":"2302.06975","title":"A Review of the Role of Causality in Developing Trustworthy AI Systems","created":"2023-02-14","cited_by_count":14,"area":null},{"id":"2204.09204","title":"Interventional Multi-Instance Learning with Deconfounded Instance-Level Prediction","created":"2022-04-20","cited_by_count":13,"area":null},{"id":"2306.07024","title":"DRCFS: Doubly Robust Causal Feature Selection","created":"2023-06-12","cited_by_count":12,"area":null},{"id":"2306.16958","title":"Identifiability of Direct Effects from Summary Causal Graphs","created":"2023-06-29","cited_by_count":12,"area":null},{"id":"2502.18848","title":"A Causal Lens for Evaluating Faithfulness Metrics","created":"2025-02-26","cited_by_count":12,"area":null},{"id":"2503.02539","title":"Disentangled Knowledge Tracing for Alleviating Cognitive Bias","created":"2025-03-04","cited_by_count":12,"area":null},{"id":"2310.07325","title":"An Adversarial Example for Direct Logit Attribution: Memory Management in GELU-4L","created":"2023-10-11","cited_by_count":11,"area":null},{"id":"2405.18836","title":"Do Finetti: On Causal Effects for Exchangeable Data","created":"2024-05-29","cited_by_count":11,"area":null},{"id":"2410.01434","title":"Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models","created":"2024-10-02","cited_by_count":11,"area":null},{"id":"2502.05390","title":"Learning Task Representations from In-Context Learning","created":"2025-02-08","cited_by_count":11,"area":null},{"id":"2502.15886","title":"A Close Look at Decomposition-based XAI-Methods for Transformer Language Models","created":"2025-02-21","cited_by_count":11,"area":null},{"id":"2503.11302","title":"Are formal and functional linguistic mechanisms dissociated in language models?","created":"2025-03-14","cited_by_count":11,"area":null},{"id":"2508.11214","title":"How Causal Abstraction Underpins Computational Explanation","created":"2025-08-15","cited_by_count":11,"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":"2202.10816","title":"Why Fair Labels Can Yield Unfair Predictions: Graphical Conditions for Introduced Unfairness","created":"2022-02-22","cited_by_count":10,"area":null},{"id":"2210.04389","title":"DeepMed: Semiparametric Causal Mediation Analysis with Debiased Deep Learning","created":"2022-10-10","cited_by_count":10,"area":null},{"id":"2401.17623","title":"Neighboring Perturbations of Knowledge Editing on Large Language Models","created":"2024-01-31","cited_by_count":10,"area":null},{"id":"2405.15443","title":"Fairness-Accuracy Trade-Offs: A Causal Perspective","created":"2024-05-24","cited_by_count":10,"area":null},{"id":"2502.11771","title":"The Validation Gap: A Mechanistic Analysis of How Language Models Compute Arithmetic but Fail to Validate It","created":"2025-02-17","cited_by_count":10,"area":null},{"id":"2605.01148","title":"Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts","created":"2026-05-01","cited_by_count":10,"area":null},{"id":"2308.01097","title":"Spatio-Temporal Branching for Motion Prediction using Motion Increments","created":"2023-08-02","cited_by_count":9,"area":null},{"id":"2310.17816","title":"Local Discovery by Partitioning: Polynomial-Time Causal Discovery Around Exposure-Outcome Pairs","created":"2023-10-25","cited_by_count":9,"area":null},{"id":"2404.06287","title":"Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training","created":"2024-04-09","cited_by_count":8,"area":null},{"id":"2602.16698","title":"Causality is Key for Interpretability Claims to Generalise","created":"2026-02-18","cited_by_count":8,"area":null},{"id":"2206.00701","title":"What Changed? Investigating Debiasing Methods using Causal Mediation Analysis","created":"2022-06-01","cited_by_count":7,"area":null},{"id":"2304.04374","title":"Partial Identification of Causal Effects Using Proxy Variables","created":"2023-04-10","cited_by_count":7,"area":null},{"id":"2305.02160","title":"Explaining Language Models' Predictions with High-Impact Concepts","created":"2023-05-03","cited_by_count":7,"area":null},{"id":"2311.00863","title":"Training Dynamics of Contextual N-Grams in Language Models","created":"2023-11-01","cited_by_count":7,"area":null},{"id":"2401.06864","title":"Deep Learning With DAGs","created":"2024-01-12","cited_by_count":7,"area":null},{"id":"2502.07620","title":"Resilient Contrastive Pre-training under Non-Stationary Drift","created":"2025-02-11","cited_by_count":7,"area":null},{"id":"2111.02927","title":"Causal Inference with Hidden Mediators","created":"2021-11-04","cited_by_count":6,"area":null},{"id":"2405.14848","title":"Local Causal Discovery for Structural Evidence of Direct Discrimination","created":"2024-05-23","cited_by_count":6,"area":null},{"id":"2509.05291","title":"Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining","created":"2025-09-05","cited_by_count":6,"area":null},{"id":"2510.08294","title":"Counterfactual Identifiability via Dynamic Optimal Transport","created":"2025-10-09","cited_by_count":6,"area":null},{"id":"2605.30233","title":"Do Language Models Track Entities Across State Changes?","created":"2026-05-28","cited_by_count":6,"area":null},{"id":"2104.13020","title":"Simple yet Sharp Sensitivity Analysis for Unmeasured Confounding","created":"2021-04-27","cited_by_count":5,"area":null},{"id":"2107.06098","title":"Using Causal Analysis for Conceptual Deep Learning Explanation","created":"2021-07-10","cited_by_count":5,"area":null},{"id":"2111.03950","title":"Sequential Kernel Embedding for Mediated and Time-Varying Dose Response Curves","created":"2021-11-06","cited_by_count":5,"area":null},{"id":"2305.13115","title":"Causal-Based Supervision of Attention in Graph Neural Network: A Better and Simpler Choice towards Powerful Attention","created":"2023-05-22","cited_by_count":5,"area":null},{"id":"2411.02461","title":"Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control","created":"2024-11-04","cited_by_count":5,"area":null},{"id":"2503.15117","title":"Exploring Model Editing for LLM-based Aspect-Based Sentiment Classification","created":"2025-03-19","cited_by_count":5,"area":null}],"next_cursor":"100"}