{"total":107,"rows":[{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639,"area":null},{"id":"2103.00453","title":"Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP","created":"2021-02-28","cited_by_count":337,"area":null},{"id":"2203.11933","title":"A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning","created":"2022-03-22","cited_by_count":104,"area":"mllm"},{"id":"2201.12091","title":"Linear Adversarial Concept Erasure","created":"2022-01-28","cited_by_count":101,"area":null},{"id":"2109.03646","title":"Sustainable Modular Debiasing of Language Models","created":"2021-09-08","cited_by_count":100,"area":null},{"id":"2110.08527","title":"An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models","created":"2021-10-16","cited_by_count":97,"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":"2112.14168","title":"A Survey on Gender Bias in Natural Language Processing","created":"2021-12-28","cited_by_count":89,"area":null},{"id":"2305.12798","title":"Word Embeddings Are Steers for Language Models","created":"2023-05-22","cited_by_count":70,"area":null},{"id":"2104.07496","title":"Unmasking the Mask -- Evaluating Social Biases in Masked Language Models","created":"2021-04-15","cited_by_count":60,"area":null},{"id":"2205.00551","title":"Gender Bias in Masked Language Models for Multiple Languages","created":"2022-05-01","cited_by_count":60,"area":null},{"id":"2402.01981","title":"Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes","created":"2024-02-03","cited_by_count":59,"area":null},{"id":"2203.09192","title":"Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists","created":"2022-03-17","cited_by_count":55,"area":null},{"id":"2210.02938","title":"Debiasing isn't enough! -- On the Effectiveness of Debiasing MLMs and their Social Biases in Downstream Tasks","created":"2022-10-06","cited_by_count":48,"area":null},{"id":"2104.06893","title":"I Wish I Would Have Loved This One, But I Didn't -- A Multilingual Dataset for Counterfactual Detection in Product Reviews","created":"2021-04-14","cited_by_count":45,"area":null},{"id":"2409.14381","title":"Investigating Layer Importance in Large Language Models","created":"2024-09-22","cited_by_count":36,"area":null},{"id":"2305.13862","title":"A Trip Towards Fairness: Bias and De-Biasing in Large Language Models","created":"2023-05-23","cited_by_count":32,"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":"2210.11471","title":"Choose Your Lenses: Flaws in Gender Bias Evaluation","created":"2022-10-20","cited_by_count":29,"area":null},{"id":"2309.03876","title":"OpinionGPT: Modelling Explicit Biases in Instruction-Tuned LLMs","created":"2023-09-07","cited_by_count":29,"area":null},{"id":"2307.08393","title":"On the application of Large Language Models for language teaching and assessment technology","created":"2023-07-17","cited_by_count":27,"area":null},{"id":"2406.11107","title":"Exploring Safety-Utility Trade-Offs in Personalized Language Models","created":"2024-06-17","cited_by_count":27,"area":null},{"id":"2302.06321","title":"Parameter-efficient Modularised Bias Mitigation via AdapterFusion","created":"2023-02-13","cited_by_count":25,"area":null},{"id":"2410.15319","title":"Causality for Large Language Models","created":"2024-10-20","cited_by_count":25,"area":null},{"id":"2210.14552","title":"A Robust Bias Mitigation Procedure Based on the Stereotype Content Model","created":"2022-10-26","cited_by_count":24,"area":null},{"id":"2109.11708","title":"Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding","created":"2021-09-24","cited_by_count":23,"area":null},{"id":"2108.12318","title":"CAPE: Context-Aware Private Embeddings for Private Language Learning","created":"2021-08-27","cited_by_count":22,"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":"2304.01666","title":"A Survey on Contextualised Semantic Shift Detection","created":"2023-04-04","cited_by_count":22,"area":null},{"id":"2207.02463","title":"Gender Biases and Where to Find Them: Exploring Gender Bias in Pre-Trained Transformer-based Language Models Using Movement Pruning","created":"2022-07-06","cited_by_count":21,"area":null},{"id":"2211.05414","title":"ADEPT: A DEbiasing PrompT Framework","created":"2022-11-10","cited_by_count":21,"area":null},{"id":"2403.08743","title":"Prompting Fairness: Integrating Causality to Debias Large Language Models","created":"2024-03-13","cited_by_count":21,"area":null},{"id":"2305.15020","title":"An Efficient Multilingual Language Model Compression through Vocabulary Trimming","created":"2023-05-24","cited_by_count":20,"area":null},{"id":"2312.05662","title":"Understanding the Effect of Model Compression on Social Bias in Large Language Models","created":"2023-12-09","cited_by_count":19,"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":"2205.15171","title":"Modular and On-demand Bias Mitigation with Attribute-Removal Subnetworks","created":"2022-05-30","cited_by_count":18,"area":null},{"id":"2204.13749","title":"Learning to Split for Automatic Bias Detection","created":"2022-04-28","cited_by_count":16,"area":null},{"id":"2306.04067","title":"An Empirical Analysis of Parameter-Efficient Methods for Debiasing Pre-Trained Language Models","created":"2023-06-06","cited_by_count":16,"area":null},{"id":"2405.09341","title":"Large Language Model Bias Mitigation from the Perspective of Knowledge Editing","created":"2024-05-15","cited_by_count":16,"area":null},{"id":"2310.12490","title":"Co$^2$PT: Mitigating Bias in Pre-trained Language Models through Counterfactual Contrastive Prompt Tuning","created":"2023-10-19","cited_by_count":15,"area":null},{"id":"2311.10395","title":"Bias A-head? Analyzing Bias in Transformer-Based Language Model Attention Heads","created":"2023-11-17","cited_by_count":14,"area":null},{"id":"2205.12593","title":"Less Learn Shortcut: Analyzing and Mitigating Learning of Spurious Feature-Label Correlation","created":"2022-05-25","cited_by_count":13,"area":null},{"id":"2408.11843","title":"Identifying and Mitigating Social Bias Knowledge in Language Models","created":"2024-08-07","cited_by_count":13,"area":null},{"id":"2109.04624","title":"Style Pooling: Automatic Text Style Obfuscation for Improved Classification Fairness","created":"2021-09-10","cited_by_count":12,"area":null},{"id":"2309.07251","title":"In-Contextual Gender Bias Suppression for Large Language Models","created":"2023-09-13","cited_by_count":12,"area":null},{"id":"2205.10762","title":"How sensitive are translation systems to extra contexts? Mitigating gender bias in Neural Machine Translation models through relevant contexts","created":"2022-05-22","cited_by_count":10,"area":null},{"id":"2301.12855","title":"How Far Can It Go?: On Intrinsic Gender Bias Mitigation for Text Classification","created":"2023-01-30","cited_by_count":10,"area":null},{"id":"2407.17688","title":"Examining the Influence of Political Bias on Large Language Model Performance in Stance Classification","created":"2024-07-25","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":"2301.12074","title":"Comparing Intrinsic Gender Bias Evaluation Measures without using Human Annotated Examples","created":"2023-01-28","cited_by_count":8,"area":null},{"id":"2401.16457","title":"Effective Controllable Bias Mitigation for Classification and Retrieval using Gate Adapters","created":"2024-01-29","cited_by_count":8,"area":null},{"id":"2402.10353","title":"Prompt-Based Bias Calibration for Better Zero/Few-Shot Learning of Language Models","created":"2024-02-15","cited_by_count":8,"area":null},{"id":"2410.03884","title":"KidLM: Advancing Language Models for Children -- Early Insights and Future Directions","created":"2024-10-04","cited_by_count":8,"area":null},{"id":"2305.14307","title":"Debiasing should be Good and Bad: Measuring the Consistency of Debiasing Techniques in Language Models","created":"2023-05-23","cited_by_count":7,"area":null},{"id":"2309.09092","title":"The Impact of Debiasing on the Performance of Language Models in Downstream Tasks is Underestimated","created":"2023-09-16","cited_by_count":7,"area":null},{"id":"2205.09867","title":"Gender Bias in Meta-Embeddings","created":"2022-05-19","cited_by_count":6,"area":null},{"id":"2210.09588","title":"Synergy with Translation Artifacts for Training and Inference in Multilingual Tasks","created":"2022-10-18","cited_by_count":6,"area":null},{"id":"2406.10130","title":"The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models","created":"2024-06-14","cited_by_count":6,"area":null},{"id":"2509.25673","title":"Mitigating Biases in Language Models via Bias Unlearning","created":"2025-09-30","cited_by_count":6,"area":"safety"},{"id":"2211.04256","title":"Bridging Fairness and Environmental Sustainability in Natural Language Processing","created":"2022-11-08","cited_by_count":5,"area":null},{"id":"2211.11087","title":"Conceptor-Aided Debiasing of Large Language Models","created":"2022-11-20","cited_by_count":5,"area":null},{"id":"2305.11789","title":"Solving NLP Problems through Human-System Collaboration: A Discussion-based Approach","created":"2023-05-19","cited_by_count":5,"area":null},{"id":"2401.08511","title":"The Gaps between Pre-train and Downstream Settings in Bias Evaluation and Debiasing","created":"2024-01-16","cited_by_count":5,"area":null},{"id":"2405.06687","title":"Hire Me or Not? Examining Language Model's Behavior with Occupation Attributes","created":"2024-05-06","cited_by_count":5,"area":null},{"id":"2501.06795","title":"Bridging the Fairness Gap: Enhancing Pre-trained Models with LLM-Generated Sentences","created":"2025-01-12","cited_by_count":5,"area":null},{"id":"2503.04372","title":"Assumed Identities: Quantifying Gender Bias in Machine Translation of Gender-Ambiguous Occupational Terms","created":"2025-03-06","cited_by_count":5,"area":null},{"id":"2310.12936","title":"A Predictive Factor Analysis of Social Biases and Task-Performance in Pretrained Masked Language Models","created":"2023-10-19","cited_by_count":4,"area":null},{"id":"2401.15535","title":"Quantifying Stereotypes in Language","created":"2024-01-28","cited_by_count":4,"area":null},{"id":"2402.14258","title":"Eagle: Ethical Dataset Given from Real Interactions","created":"2024-02-22","cited_by_count":4,"area":null},{"id":"2406.12634","title":"News Without Borders: Domain Adaptation of Multilingual Sentence Embeddings for Cross-lingual News Recommendation","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2409.17663","title":"Explanation Bottleneck Models","created":"2024-09-26","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":"2406.13556","title":"Evaluating Short-Term Temporal Fluctuations of Social Biases in Social Media Data and Masked Language Models","created":"2024-06-19","cited_by_count":3,"area":null},{"id":"2407.11203","title":"The Life Cycle of Large Language Models: A Review of Biases in Education","created":"2024-06-03","cited_by_count":3,"area":null},{"id":"2501.01168","title":"Blind Men and the Elephant: Diverse Perspectives on Gender Stereotypes in Benchmark Datasets","created":"2025-01-02","cited_by_count":3,"area":null},{"id":"2506.05610","title":"Mitigating Confounding in Speech-Based Dementia Detection through Weight Masking","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2203.05140","title":"Speciesist Language and Nonhuman Animal Bias in English Masked Language Models","created":"2022-03-10","cited_by_count":2,"area":null},{"id":"2208.10734","title":"Learning Dynamic Contextualised Word Embeddings via Template-based Temporal Adaptation","created":"2022-08-23","cited_by_count":2,"area":null},{"id":"2305.19294","title":"Investigating the Effects of Fairness Interventions Using Pointwise Representational Similarity","created":"2023-05-30","cited_by_count":2,"area":null},{"id":"2311.13892","title":"General Phrase Debiaser: Debiasing Masked Language Models at a Multi-Token Level","created":"2023-11-23","cited_by_count":2,"area":null},{"id":"2406.00787","title":"Applying Intrinsic Debiasing on Downstream Tasks: Challenges and Considerations for Machine Translation","created":"2024-06-02","cited_by_count":2,"area":null},{"id":"2408.09489","title":"REFINE-LM: Mitigating Language Model Stereotypes via Reinforcement Learning","created":"2024-08-18","cited_by_count":2,"area":null},{"id":"2502.21123","title":"Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models","created":"2025-02-28","cited_by_count":2,"area":null},{"id":"2505.17131","title":"Relative Bias: A Comparative Framework for Quantifying Bias in LLMs","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2508.17948","title":"Debiasing Multilingual LLMs in Cross-lingual Latent Space","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2510.10943","title":"The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems","created":"2025-10-13","cited_by_count":2,"area":"agents"},{"id":"2210.10012","title":"Log-linear Guardedness and its Implications","created":"2022-10-18","cited_by_count":1,"area":null},{"id":"2402.14208","title":"LLM-Assisted Content Conditional Debiasing for Fair Text Embedding","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2402.16458","title":"ID-XCB: Data-independent Debiasing for Fair and Accurate Transformer-based Cyberbullying Detection","created":"2024-02-26","cited_by_count":1,"area":null},{"id":"2404.11782","title":"REQUAL-LM: Reliability and Equity through Aggregation in Large Language Models","created":"2024-04-17","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":"2502.15600","title":"Robust Bias Detection in MLMs and its Application to Human Trait Ratings","created":"2025-02-21","cited_by_count":1,"area":null},{"id":"2503.06734","title":"Gender Encoding Patterns in Pretrained Language Model Representations","created":"2025-03-09","cited_by_count":1,"area":null},{"id":"2509.04515","title":"Mitigation of Gender and Ethnicity Bias in AI-Generated Stories through Model Explanations","created":"2025-09-03","cited_by_count":1,"area":null},{"id":"2509.16462","title":"Let's Unlearn Stereotypes Before Decision-Making: Assessing the Impact of Intrinsic Bias Mitigation on Downstream Fairness in LLMs","created":"2025-09-19","cited_by_count":1,"area":"safety"},{"id":"2605.02640","title":"Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2605.16113","title":"DebiasRAG: A Tuning-Free Path to Fair Generation in Large Language Models through Retrieval-Augmented Generation","created":"2026-05-15","cited_by_count":1,"area":"rag"},{"id":"2608.00622","title":"A Heuristic Perspective on Debiasing Language Models","created":"2026-08-01","cited_by_count":1,"area":null},{"id":"2205.07603","title":"Assessing the Limits of the Distributional Hypothesis in Semantic Spaces: Trait-based Relational Knowledge and the Impact of Co-occurrences","created":"2022-05-16","cited_by_count":0,"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}],"next_cursor":"100"}