{"total":280,"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":"2309.16042","title":"Towards Best Practices of Activation Patching in Language Models: Metrics and Methods","created":"2023-09-27","cited_by_count":359,"area":"mechinterp"},{"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":"2402.13950","title":"Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning","created":"2024-02-21","cited_by_count":110,"area":"lr"},{"id":"2310.08744","title":"Circuit Component Reuse Across Tasks in Transformer Language Models","created":"2023-10-12","cited_by_count":108,"area":"mechinterp"},{"id":"2410.21272","title":"Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics","created":"2024-10-28","cited_by_count":97,"area":"lr"},{"id":"2305.15054","title":"A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis","created":"2023-05-24","cited_by_count":89,"area":"lr"},{"id":"2201.01490","title":"Debiased Learning from Naturally Imbalanced Pseudo-Labels","created":"2022-01-05","cited_by_count":85,"area":null},{"id":"2311.17030","title":"Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching","created":"2023-11-28","cited_by_count":80,"area":"mechinterp"},{"id":"2402.17700","title":"RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations","created":"2024-02-27","cited_by_count":79,"area":"mechinterp"},{"id":"2210.12023","title":"A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models","created":"2022-10-21","cited_by_count":68,"area":"lr"},{"id":"2308.14179","title":"Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP","created":"2023-08-27","cited_by_count":62,"area":"mechinterp"},{"id":"2405.17969","title":"Knowledge Circuits in Pretrained Transformers","created":"2024-05-28","cited_by_count":60,"area":"mechinterp"},{"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":"2504.13151","title":"MIB: A Mechanistic Interpretability Benchmark","created":"2025-04-17","cited_by_count":56,"area":"mechinterp"},{"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":"2406.15334","title":"Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning","created":"2024-06-21","cited_by_count":50,"area":"mllm"},{"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":"2406.04236","title":"Understanding Information Storage and Transfer in Multi-modal Large Language Models","created":"2024-06-06","cited_by_count":49,"area":"mllm"},{"id":"2409.01659","title":"Interpreting and Improving Large Language Models in Arithmetic Calculation","created":"2024-09-03","cited_by_count":45,"area":null},{"id":"2406.19501","title":"Monitoring Latent World States in Language Models with Propositional Probes","created":"2024-06-27","cited_by_count":43,"area":"wm"},{"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":"2404.03646","title":"Locating and Editing Factual Associations in Mamba","created":"2024-04-04","cited_by_count":37,"area":"ssm"},{"id":"2506.09047","title":"Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs","created":"2025-06-10","cited_by_count":35,"area":"mllm"},{"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":"2502.17516","title":"A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models","created":"2025-02-22","cited_by_count":34,"area":"mllm"},{"id":"2509.23886","title":"Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer","created":"2025-09-28","cited_by_count":34,"area":"distill"},{"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":"2502.20332","title":"Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models","created":"2025-02-27","cited_by_count":31,"area":"lr"},{"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":"2403.02738","title":"Causal Prompting: Debiasing Large Language Model Prompting based on Front-Door Adjustment","created":"2024-03-05","cited_by_count":30,"area":"lr"},{"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":"2601.22594","title":"Language Model Circuits Are Sparse in the Neuron Basis","created":"2026-01-30","cited_by_count":25,"area":"mechinterp"},{"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":"2408.01416","title":"The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis","created":"2024-08-02","cited_by_count":24,"area":"mechinterp"},{"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":"2405.12522","title":"Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models","created":"2024-05-21","cited_by_count":15,"area":"mechinterp"},{"id":"2410.22330","title":"Vision-Language Models Create Cross-Modal Task Representations","created":"2024-10-29","cited_by_count":15,"area":"mllm"},{"id":"2510.00845","title":"Mechanistic Interpretability as Statistical Estimation: A Variance Analysis","created":"2025-10-01","cited_by_count":15,"area":"mechinterp"},{"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":"2408.09916","title":"Attribution Analysis Meets Model Editing: Advancing Knowledge Correction in Vision Language Models with VisEdit","created":"2024-08-19","cited_by_count":14,"area":"mllm"},{"id":"2502.04577","title":"Position-aware Automatic Circuit Discovery","created":"2025-02-07","cited_by_count":14,"area":"mechinterp"},{"id":"2204.09204","title":"Interventional Multi-Instance Learning with Deconfounded Instance-Level Prediction","created":"2022-04-20","cited_by_count":13,"area":null},{"id":"2310.19559","title":"Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning","created":"2023-10-30","cited_by_count":13,"area":"lr"},{"id":"2506.15871","title":"Visual symbolic mechanisms: Emergent symbol processing in vision language models","created":"2025-06-18","cited_by_count":13,"area":"mllm"},{"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":"2312.07876","title":"Causality Analysis for Evaluating the Security of Large Language Models","created":"2023-12-13","cited_by_count":11,"area":"alignment"},{"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}],"next_cursor":"100"}