{"total":25,"rows":[{"id":"2201.12091","title":"Linear Adversarial Concept Erasure","created":"2022-01-28","cited_by_count":101,"area":null},{"id":"2201.12191","title":"Kernelized Concept Erasure","created":"2022-01-28","cited_by_count":48,"area":null},{"id":"2105.07109","title":"The Low-Dimensional Linear Geometry of Contextualized Word Representations","created":"2021-05-15","cited_by_count":40,"area":null},{"id":"2504.02922","title":"Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning","created":"2025-04-03","cited_by_count":34,"area":null},{"id":"2111.04158","title":"A Word on Machine Ethics: A Response to Jiang et al. (2021)","created":"2021-11-07","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":"2211.05617","title":"Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey","created":"2022-11-10","cited_by_count":22,"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":"2109.04732","title":"Assessing the Reliability of Word Embedding Gender Bias Measures","created":"2021-09-10","cited_by_count":14,"area":null},{"id":"2411.07180","title":"Gumbel Counterfactual Generation From Language Models","created":"2024-11-11","cited_by_count":14,"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":"2408.15510","title":"How Reliable are Causal Probing Interventions?","created":"2024-08-28","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":"2103.03598","title":"WordBias: An Interactive Visual Tool for Discovering Intersectional Biases Encoded in Word Embeddings","created":"2021-03-05","cited_by_count":8,"area":null},{"id":"2509.17196","title":"Evolution of Concepts in Language Model Pre-Training","created":"2025-09-21","cited_by_count":8,"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":"2110.05301","title":"On a Benefit of Mask Language Modeling: Robustness to Simplicity Bias","created":"2021-10-11","cited_by_count":4,"area":null},{"id":"2303.00333","title":"Competence-Based Analysis of Language Models","created":"2023-03-01","cited_by_count":4,"area":null},{"id":"2507.12341","title":"Nonlinear Concept Erasure: a Density Matching Approach","created":"2025-07-16","cited_by_count":3,"area":null},{"id":"2310.17010","title":"This Reads Like That: Deep Learning for Interpretable Natural Language Processing","created":"2023-10-25","cited_by_count":2,"area":null},{"id":"2212.07547","title":"Unsupervised Detection of Contextualized Embedding Bias with Application to Ideology","created":"2022-12-14","cited_by_count":1,"area":null},{"id":"2306.07427","title":"Towards Fair and Explainable AI using a Human-Centered AI Approach","created":"2023-06-12","cited_by_count":1,"area":null},{"id":"2504.16884","title":"Do Large Language Models know who did what to whom?","created":"2025-04-23","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}],"next_cursor":null}