{"total":34,"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":"2109.05704","title":"Mitigating Language-Dependent Ethnic Bias in BERT","created":"2021-09-13","cited_by_count":87,"area":null},{"id":"2205.02526","title":"Theories of \"Gender\" in NLP Bias Research","created":"2022-05-05","cited_by_count":62,"area":null},{"id":"2110.00672","title":"Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models","created":"2021-10-01","cited_by_count":39,"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":"2305.10204","title":"Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projection","created":"2023-05-17","cited_by_count":25,"area":null},{"id":"2206.03390","title":"Gender Bias in Word Embeddings: A Comprehensive Analysis of Frequency, Syntax, and Semantics","created":"2022-06-07","cited_by_count":24,"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":"2106.10826","title":"Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification","created":"2021-06-21","cited_by_count":20,"area":null},{"id":"2203.07523","title":"Sense Embeddings are also Biased--Evaluating Social Biases in Static and Contextualised Sense Embeddings","created":"2022-03-14","cited_by_count":18,"area":null},{"id":"2207.10245","title":"The Birth of Bias: A case study on the evolution of gender bias in an English language model","created":"2022-07-21","cited_by_count":16,"area":null},{"id":"2307.04303","title":"Learning to Generate Equitable Text in Dialogue from Biased Training Data","created":"2023-07-10","cited_by_count":12,"area":null},{"id":"2412.11679","title":"Bias Vector: Mitigating Biases in Language Models with Task Arithmetic Approach","created":"2024-12-16","cited_by_count":12,"area":null},{"id":"2112.05194","title":"Word Embeddings via Causal Inference: Gender Bias Reducing and Semantic Information Preserving","created":"2021-12-09","cited_by_count":11,"area":null},{"id":"2312.07751","title":"Large Human Language Models: A Need and the Challenges","created":"2023-11-09","cited_by_count":11,"area":null},{"id":"2603.07368","title":"Position: LLMs Must Use Functor-Based and RAG-Driven Bias Mitigation for Fairness","created":"2026-03-07","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":"2603.21524","title":"CatRAG: Functor-Guided Structural Debiasing with Retrieval Augmentation for Fair LLMs","created":"2026-03-23","cited_by_count":9,"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":"2109.14039","title":"Marked Attribute Bias in Natural Language Inference","created":"2021-09-28","cited_by_count":6,"area":null},{"id":"2205.09867","title":"Gender Bias in Meta-Embeddings","created":"2022-05-19","cited_by_count":6,"area":null},{"id":"2503.15815","title":"Attention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing","created":"2025-03-20","cited_by_count":5,"area":null},{"id":"2311.12689","title":"Fair Text Classification with Wasserstein Independence","created":"2023-11-21","cited_by_count":4,"area":null},{"id":"2503.06792","title":"On the Mutual Influence of Gender and Occupation in LLM Representations","created":"2025-03-09","cited_by_count":4,"area":null},{"id":"2104.02797","title":"VERB: Visualizing and Interpreting Bias Mitigation Techniques for Word Representations","created":"2021-04-06","cited_by_count":3,"area":null},{"id":"2405.09543","title":"Algorithmic Fairness: A Tolerance Perspective","created":"2024-04-26","cited_by_count":2,"area":null},{"id":"2107.11956","title":"Preliminary Steps Towards Federated Sentiment Classification","created":"2021-07-26","cited_by_count":1,"area":null},{"id":"2110.01094","title":"Adversarial Examples Generation for Reducing Implicit Gender Bias in Pre-trained Models","created":"2021-10-03","cited_by_count":1,"area":null},{"id":"2207.08104","title":"A Multibias-mitigated and Sentiment Knowledge Enriched Transformer for Debiasing in Multimodal Conversational Emotion Recognition","created":"2022-07-17","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":"2411.12074","title":"Mitigating Gender Bias in Contextual Word Embeddings","created":"2024-11-18","cited_by_count":1,"area":null},{"id":"2511.00519","title":"Exploring and Mitigating Gender Bias in Encoder-Based Transformer Models","created":"2025-11-01","cited_by_count":1,"area":null},{"id":"2305.14574","title":"Detecting and Mitigating Indirect Stereotypes in Word Embeddings","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2604.08561","title":"A Representation-Level Assessment of Bias Mitigation in Foundation Models","created":"2026-03-17","cited_by_count":0,"area":null}],"next_cursor":null}