{"total":78,"rows":[{"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":"2306.03819","title":"LEACE: Perfect linear concept erasure in closed form","created":"2023-06-06","cited_by_count":267,"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":"2404.03592","title":"ReFT: Representation Finetuning for Language Models","created":"2024-04-04","cited_by_count":197,"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":"2308.10149","title":"A Survey on Fairness in Large Language Models","created":"2023-08-20","cited_by_count":95,"area":null},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2204.08831","title":"Probing for the Usage of Grammatical Number","created":"2022-04-19","cited_by_count":59,"area":null},{"id":"2211.14946","title":"Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation Models","created":"2022-11-27","cited_by_count":57,"area":null},{"id":"2207.04153","title":"Probing Classifiers are Unreliable for Concept Removal and Detection","created":"2022-07-08","cited_by_count":41,"area":null},{"id":"2507.16795","title":"Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning","created":"2025-07-22","cited_by_count":39,"area":null},{"id":"2206.09191","title":"Gender Artifacts in Visual Datasets","created":"2022-06-18","cited_by_count":38,"area":null},{"id":"2402.16382","title":"Immunization against harmful fine-tuning attacks","created":"2024-02-26","cited_by_count":35,"area":null},{"id":"2203.07893","title":"Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information","created":"2022-03-15","cited_by_count":34,"area":null},{"id":"2210.14975","title":"MABEL: Attenuating Gender Bias using Textual Entailment Data","created":"2022-10-26","cited_by_count":31,"area":null},{"id":"2302.06321","title":"Parameter-efficient Modularised Bias Mitigation via AdapterFusion","created":"2023-02-13","cited_by_count":25,"area":null},{"id":"2305.10204","title":"Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projection","created":"2023-05-17","cited_by_count":25,"area":null},{"id":"2307.15054","title":"A Geometric Notion of Causal Probing","created":"2023-07-27","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":"2302.13319","title":"Efficient fair PCA for fair representation learning","created":"2023-02-26","cited_by_count":23,"area":null},{"id":"2411.07404","title":"Controllable Context Sensitivity and the Knob Behind It","created":"2024-11-11","cited_by_count":23,"area":null},{"id":"2212.10563","title":"BLIND: Bias Removal With No Demographics","created":"2022-12-20","cited_by_count":22,"area":null},{"id":"2307.01595","title":"Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases","created":"2023-07-04","cited_by_count":21,"area":null},{"id":"2404.11534","title":"Decomposing and Editing Predictions by Modeling Model Computation","created":"2024-04-17","cited_by_count":19,"area":null},{"id":"2212.04273","title":"Better Hit the Nail on the Head than Beat around the Bush: Removing Protected Attributes with a Single Projection","created":"2022-12-08","cited_by_count":17,"area":null},{"id":"2403.09053","title":"Towards a theory of model distillation","created":"2024-03-14","cited_by_count":15,"area":null},{"id":"2208.08176","title":"Visual Comparison of Language Model Adaptation","created":"2022-08-17","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":"2311.04354","title":"Uncovering Intermediate Variables in Transformers using Circuit Probing","created":"2023-11-07","cited_by_count":12,"area":null},{"id":"2510.15804","title":"Emergence of Linear Truth Encodings in Language Models","created":"2025-10-17","cited_by_count":12,"area":null},{"id":"2312.00194","title":"Robust Concept Erasure via Kernelized Rate-Distortion Maximization","created":"2023-11-30","cited_by_count":11,"area":null},{"id":"2602.15293","title":"The Information Geometry of Softmax: Probing and Steering","created":"2026-02-17","cited_by_count":11,"area":null},{"id":"2204.09168","title":"Analyzing Gender Representation in Multilingual Models","created":"2022-04-20","cited_by_count":10,"area":null},{"id":"2205.06135","title":"Fair NLP Models with Differentially Private Text Encoders","created":"2022-05-12","cited_by_count":9,"area":null},{"id":"2412.13341","title":"Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing","created":"2024-12-17","cited_by_count":8,"area":null},{"id":"2302.02997","title":"Erasure of Unaligned Attributes from Neural Representations","created":"2023-02-06","cited_by_count":6,"area":null},{"id":"2310.11991","title":"Removing Spurious Concepts from Neural Network Representations via Joint Subspace Estimation","created":"2023-10-18","cited_by_count":6,"area":null},{"id":"2503.20098","title":"Fundamental Limits of Perfect Concept Erasure","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2305.16863","title":"Controlling Learned Effects to Reduce Spurious Correlations in Text Classifiers","created":"2023-05-26","cited_by_count":5,"area":null},{"id":"2310.18593","title":"Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint","created":"2023-10-28","cited_by_count":5,"area":null},{"id":"2303.00333","title":"Competence-Based Analysis of Language Models","created":"2023-03-01","cited_by_count":4,"area":null},{"id":"2406.09855","title":"On the Encoding of Gender in Transformer-based ASR Representations","created":"2024-06-14","cited_by_count":4,"area":null},{"id":"2504.03933","title":"Language Models Are Implicitly Continuous","created":"2025-04-04","cited_by_count":4,"area":null},{"id":"2506.06686","title":"Learning Distribution-Wise Control in Representation Space for Language Models","created":"2025-06-07","cited_by_count":4,"area":null},{"id":"2506.10703","title":"Preserving Task-Relevant Information Under Linear Concept Removal","created":"2025-06-12","cited_by_count":4,"area":null},{"id":"2210.08758","title":"Systematic Evaluation of Predictive Fairness","created":"2022-10-17","cited_by_count":3,"area":null},{"id":"2310.07837","title":"Measuring Feature Sparsity in Language Models","created":"2023-10-11","cited_by_count":3,"area":null},{"id":"2507.12341","title":"Nonlinear Concept Erasure: a Density Matching Approach","created":"2025-07-16","cited_by_count":3,"area":null},{"id":"2605.11410","title":"What Do EEG Foundation Models Capture from Human Brain Signals?","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2310.15114","title":"How To Build Competitive Multi-gender Speech Translation Models For Controlling Speaker Gender Translation","created":"2023-10-23","cited_by_count":2,"area":null},{"id":"2501.10150","title":"Dual Debiasing: Remove Stereotypes and Keep Factual Gender for Fair Language Modeling and Translation","created":"2025-01-17","cited_by_count":2,"area":null},{"id":"2603.07529","title":"Obliviator Reveals the Cost of Nonlinear Guardedness in Concept Erasure","created":"2026-03-08","cited_by_count":2,"area":null},{"id":"2604.22128","title":"Dissociating Decodability and Causal Use in Bracket-Sequence Transformers","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2210.10012","title":"Log-linear Guardedness and its Implications","created":"2022-10-18","cited_by_count":1,"area":null},{"id":"2212.08054","title":"DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialogue","created":"2022-12-15","cited_by_count":1,"area":null},{"id":"2410.04472","title":"Collapsed Language Models Promote Fairness","created":"2024-10-06","cited_by_count":1,"area":null},{"id":"2601.23157","title":"No More, No Less: Least-Privilege Language Models","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2605.06640","title":"Concept-Based Abductive and Contrastive Explanations for Behaviors of Vision Models","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.27676","title":"Unsupervised Identification and Removal of Spurious Correlations During Fine-Tuning","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2608.10566","title":"Iterative Erasure Count Is Not an Affine-Invariant Concept Dimension","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2406.04876","title":"HateDebias: On the Diversity and Variability of Hate Speech Debiasing","created":"2024-06-07","cited_by_count":0,"area":null},{"id":"2501.00885","title":"Representation in large language models","created":"2025-01-01","cited_by_count":0,"area":null},{"id":"2504.06470","title":"Deep Fair Learning: Task-Aware Fair Representations via Joint Distance-Covariance Regularization","created":"2025-04-08","cited_by_count":0,"area":null},{"id":"2510.23935","title":"Understanding Fairness and Prediction Error through Subspace Decomposition and Influence Analysis","created":"2025-10-27","cited_by_count":0,"area":null},{"id":"2604.05296","title":"From Measurement to Mitigation: Quantifying and Reducing Identity Leakage in Image Representation Encoders with Linear Subspace Removal","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2605.07631","title":"Inference Time Causal Probing in LLMs","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.25156","title":"Abduction-Deduction Entanglement: Domain Generalization via Representation Transplants","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2606.09411","title":"Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.10669","title":"In Defense of Information Leakage in Concept-based Models","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.11661","title":"Learning Instance-Adaptive Low-Rank Orthogonal Subspaces for Clothes-Changing Person Re-Identification","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2607.03973","title":"MANCE: Manifold Aware Concept Erasure","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2607.09306","title":"Exposure is not manifestation: measurement target and output resolution jointly determine which behavioural-faithfulness evaluator wins","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2609.11253","title":"MUtE: A Dual Framework for Concept Erasure and Counterfactual Interventions","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.22337","title":"When and Why Do Linear Bias Probes Fail? A Geometric and Statistical Theory of Bias Detectability in Large Language Model Representations","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2609.27593","title":"Hidden not Deleted: How Networks Suppress Entangled Features","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.36451","title":"Invariant Atoms: Sparse Coordinates of Local Semantic Geometry in Language Model Representations","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.05017","title":"Operational Abstractions of Neural Network Concepts via Topological Representations","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.07798","title":"Thin Evidence, Thick Priors: How Language Models Substitute Identity for Missing Financial Facts","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}