{"total":200,"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":"2105.03075","title":"A Survey of Data Augmentation Approaches for NLP","created":"2021-05-07","cited_by_count":409,"area":null},{"id":"2105.04054","title":"Societal Biases in Language Generation: Progress and Challenges","created":"2021-05-10","cited_by_count":202,"area":null},{"id":"2109.00725","title":"Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond","created":"2021-09-02","cited_by_count":178,"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":"2201.05273","title":"Pretrained Language Models for Text Generation: A Survey","created":"2022-01-14","cited_by_count":122,"area":null},{"id":"2104.06001","title":"Gender Bias in Machine Translation","created":"2021-04-13","cited_by_count":117,"area":null},{"id":"2101.09523","title":"Debiasing Pre-trained Contextualised Embeddings","created":"2021-01-23","cited_by_count":107,"area":null},{"id":"2101.09995","title":"Re-imagining Algorithmic Fairness in India and Beyond","created":"2021-01-25","cited_by_count":104,"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":"2110.01852","title":"Data Augmentation Approaches in Natural Language Processing: A Survey","created":"2021-10-05","cited_by_count":82,"area":null},{"id":"2108.03362","title":"On Measures of Biases and Harms in NLP","created":"2021-08-07","cited_by_count":81,"area":null},{"id":"2411.10915","title":"Bias in Large Language Models: Origin, Evaluation, and Mitigation","created":"2024-11-16","cited_by_count":77,"area":null},{"id":"2310.12560","title":"Fast Model Debias with Machine Unlearning","created":"2023-10-19","cited_by_count":72,"area":"safety"},{"id":"2205.02526","title":"Theories of \"Gender\" in NLP Bias Research","created":"2022-05-05","cited_by_count":62,"area":null},{"id":"2105.06965","title":"Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction","created":"2021-05-14","cited_by_count":59,"area":null},{"id":"2404.01349","title":"Fairness in Large Language Models: A Taxonomic Survey","created":"2024-03-31","cited_by_count":58,"area":null},{"id":"2205.12586","title":"Perturbation Augmentation for Fairer NLP","created":"2022-05-25","cited_by_count":52,"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":"2201.09119","title":"A Causal Lens for Controllable Text Generation","created":"2022-01-22","cited_by_count":45,"area":null},{"id":"2212.01488","title":"Event knowledge in large language models: the gap between the impossible and the unlikely","created":"2022-12-02","cited_by_count":45,"area":null},{"id":"2405.10431","title":"Thinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Models","created":"2024-05-16","cited_by_count":45,"area":"lr"},{"id":"2310.00603","title":"Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals","created":"2023-10-01","cited_by_count":44,"area":null},{"id":"2107.00753","title":"An Investigation of the (In)effectiveness of Counterfactually Augmented Data","created":"2021-07-01","cited_by_count":42,"area":null},{"id":"2206.01161","title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","created":"2022-06-02","cited_by_count":41,"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":"2203.12574","title":"Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal","created":"2022-03-23","cited_by_count":40,"area":"distill"},{"id":"2407.03129","title":"Social Bias Evaluation for Large Language Models Requires Prompt Variations","created":"2024-07-03","cited_by_count":40,"area":null},{"id":"2504.14492","title":"FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering","created":"2025-04-20","cited_by_count":40,"area":"mechinterp"},{"id":"2404.17218","title":"Prompting Techniques for Reducing Social Bias in LLMs through System 1 and System 2 Cognitive Processes","created":"2024-04-26","cited_by_count":39,"area":null},{"id":"2110.14375","title":"Perceptual Score: What Data Modalities Does Your Model Perceive?","created":"2021-10-27","cited_by_count":35,"area":null},{"id":"2210.04492","title":"Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization","created":"2022-10-10","cited_by_count":33,"area":null},{"id":"2408.03907","title":"Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Models","created":"2024-08-07","cited_by_count":33,"area":null},{"id":"2307.01503","title":"On Evaluating and Mitigating Gender Biases in Multilingual Settings","created":"2023-07-04","cited_by_count":31,"area":null},{"id":"2106.01127","title":"Towards Robust Classification Model by Counterfactual and Invariant Data Generation","created":"2021-06-02","cited_by_count":30,"area":null},{"id":"2106.15231","title":"Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysis","created":"2021-06-29","cited_by_count":30,"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":"2106.00169","title":"Gender Bias Amplification During Speed-Quality Optimization in Neural Machine Translation","created":"2021-06-01","cited_by_count":28,"area":null},{"id":"2306.04597","title":"Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data Interventions","created":"2023-06-07","cited_by_count":28,"area":null},{"id":"2110.03212","title":"Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates","created":"2021-10-07","cited_by_count":27,"area":null},{"id":"2309.14381","title":"Survey of Social Bias in Vision-Language Models","created":"2023-09-24","cited_by_count":26,"area":"mllm"},{"id":"2406.01285","title":"Large Language Models as Recommender Systems: A Study of Popularity Bias","created":"2024-06-03","cited_by_count":26,"area":null},{"id":"2101.00411","title":"Substructure Substitution: Structured Data Augmentation for NLP","created":"2021-01-02","cited_by_count":25,"area":null},{"id":"2307.10514","title":"Building Socio-culturally Inclusive Stereotype Resources with Community Engagement","created":"2023-07-20","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":"2101.09525","title":"Dictionary-based Debiasing of Pre-trained Word Embeddings","created":"2021-01-23","cited_by_count":24,"area":null},{"id":"2310.18913","title":"Debiasing Algorithm through Model Adaptation","created":"2023-10-29","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":"2203.09866","title":"Under the Morphosyntactic Lens: A Multifaceted Evaluation of Gender Bias in Speech Translation","created":"2022-03-18","cited_by_count":23,"area":null},{"id":"2112.05746","title":"On Causally Disentangled Representations","created":"2021-12-10","cited_by_count":22,"area":null},{"id":"2210.07269","title":"SODAPOP: Open-Ended Discovery of Social Biases in Social Commonsense Reasoning Models","created":"2022-10-13","cited_by_count":22,"area":"lr"},{"id":"2310.12611","title":"Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model","created":"2023-10-19","cited_by_count":22,"area":null},{"id":"2109.02444","title":"Top-N Recommendation with Counterfactual User Preference Simulation","created":"2021-09-02","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":"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":"2205.07043","title":"Naturalistic Causal Probing for Morpho-Syntax","created":"2022-05-14","cited_by_count":19,"area":null},{"id":"2204.04026","title":"Fair and Argumentative Language Modeling for Computational Argumentation","created":"2022-04-08","cited_by_count":18,"area":null},{"id":"2303.03975","title":"GATE: A Challenge Set for Gender-Ambiguous Translation Examples","created":"2023-03-07","cited_by_count":18,"area":null},{"id":"2503.08588","title":"BiasEdit: Debiasing Stereotyped Language Models via Model Editing","created":"2025-03-11","cited_by_count":18,"area":null},{"id":"2204.07359","title":"Text Revision by On-the-Fly Representation Optimization","created":"2022-04-15","cited_by_count":17,"area":null},{"id":"2407.15366","title":"Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias","created":"2024-07-22","cited_by_count":17,"area":null},{"id":"2205.12640","title":"Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typing","created":"2022-05-25","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":"2406.02378","title":"On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept","created":"2024-06-04","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":"2506.05166","title":"Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective","created":"2025-06-05","cited_by_count":15,"area":"mechinterp"},{"id":"2305.11140","title":"Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model","created":"2023-05-18","cited_by_count":14,"area":null},{"id":"2310.10310","title":"Investigating Bias in Multilingual Language Models: Cross-Lingual Transfer of Debiasing Techniques","created":"2023-10-16","cited_by_count":14,"area":null},{"id":"2310.12803","title":"Data Augmentations for Improved (Large) Language Model Generalization","created":"2023-10-19","cited_by_count":14,"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":"2503.05371","title":"Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs","created":"2025-03-07","cited_by_count":14,"area":"mechinterp"},{"id":"2403.09963","title":"Take Care of Your Prompt Bias! Investigating and Mitigating Prompt Bias in Factual Knowledge Extraction","created":"2024-03-15","cited_by_count":13,"area":null},{"id":"2407.05740","title":"Do Multilingual Large Language Models Mitigate Stereotype Bias?","created":"2024-07-08","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":"2506.05339","title":"Flattery, Fluff, and Fog: Diagnosing and Mitigating Idiosyncratic Biases in Preference Models","created":"2025-06-05","cited_by_count":13,"area":"alignment"},{"id":"2110.09216","title":"The Arabic Parallel Gender Corpus 2.0: Extensions and Analyses","created":"2021-10-18","cited_by_count":12,"area":null},{"id":"2307.10522","title":"Gender-tuning: Empowering Fine-tuning for Debiasing Pre-trained Language Models","created":"2023-07-20","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":"2310.09624","title":"ASSERT: Automated Safety Scenario Red Teaming for Evaluating the Robustness of Large Language Models","created":"2023-10-14","cited_by_count":12,"area":"safety"},{"id":"2403.14409","title":"Locating and Mitigating Gender Bias in Large Language Models","created":"2024-03-21","cited_by_count":12,"area":null},{"id":"2407.13710","title":"OxonFair: A Flexible Toolkit for Algorithmic Fairness","created":"2024-06-30","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":"2105.13782","title":"How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation","created":"2021-05-28","cited_by_count":11,"area":null},{"id":"2107.05987","title":"Generating Gender Augmented Data for NLP","created":"2021-07-13","cited_by_count":11,"area":null},{"id":"2312.01509","title":"Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societies","created":"2023-12-03","cited_by_count":11,"area":null},{"id":"2111.12490","title":"Matching Learned Causal Effects of Neural Networks with Domain Priors","created":"2021-11-24","cited_by_count":10,"area":null},{"id":"2204.09168","title":"Analyzing Gender Representation in Multilingual Models","created":"2022-04-20","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":"2306.02842","title":"Improving Conversational Recommendation Systems via Counterfactual Data Simulation","created":"2023-06-05","cited_by_count":10,"area":null},{"id":"2402.13462","title":"Potential and Challenges of Model Editing for Social Debiasing","created":"2024-02-21","cited_by_count":10,"area":null},{"id":"2109.04053","title":"Table-based Fact Verification with Salience-aware Learning","created":"2021-09-09","cited_by_count":9,"area":null},{"id":"2407.08441","title":"Are Large Language Models Really Bias-Free? Jailbreak Prompts for Assessing Adversarial Robustness to Bias Elicitation","created":"2024-07-11","cited_by_count":9,"area":"safety"},{"id":"2104.08735","title":"Learning with Instance Bundles for Reading Comprehension","created":"2021-04-18","cited_by_count":8,"area":null},{"id":"2203.10675","title":"Mitigating Gender Bias in Machine Translation through Adversarial Learning","created":"2022-03-20","cited_by_count":8,"area":null},{"id":"2204.10365","title":"Towards an Enhanced Understanding of Bias in Pre-trained Neural Language Models: A Survey with Special Emphasis on Affective Bias","created":"2022-04-21","cited_by_count":8,"area":null},{"id":"2207.10032","title":"Detecting Harmful Online Conversational Content towards LGBTQIA+ Individuals","created":"2022-06-15","cited_by_count":8,"area":null},{"id":"2310.08795","title":"Mitigating Bias for Question Answering Models by Tracking Bias Influence","created":"2023-10-13","cited_by_count":8,"area":null}],"next_cursor":"100"}