{"total":349,"rows":[{"id":"2303.17548","title":"Whose Opinions Do Language Models Reflect?","created":"2023-03-30","cited_by_count":773,"area":null},{"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":"2112.10668","title":"Few-shot Learning with Multilingual Language Models","created":"2021-12-20","cited_by_count":278,"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":"2211.03759","title":"Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale","created":"2022-11-07","cited_by_count":262,"area":null},{"id":"2310.09219","title":"\"Kelly is a Warm Person, Joseph is a Role Model\": Gender Biases in LLM-Generated Reference Letters","created":"2023-10-13","cited_by_count":199,"area":null},{"id":"2310.16218","title":"Knowledge Editing for Large Language Models: A Survey","created":"2023-10-24","cited_by_count":194,"area":"lr"},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163,"area":null},{"id":"2304.00740","title":"Inspecting and Editing Knowledge Representations in Language Models","created":"2023-04-03","cited_by_count":141,"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":"2108.12084","title":"Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies","created":"2021-08-27","cited_by_count":128,"area":null},{"id":"2110.06733","title":"Systematic Inequalities in Language Technology Performance across the World's Languages","created":"2021-10-13","cited_by_count":120,"area":null},{"id":"2207.00220","title":"Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset","created":"2022-07-01","cited_by_count":113,"area":null},{"id":"2310.17191","title":"How do Language Models Bind Entities in Context?","created":"2023-10-26","cited_by_count":108,"area":null},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107,"area":null},{"id":"2201.12091","title":"Linear Adversarial Concept Erasure","created":"2022-01-28","cited_by_count":101,"area":null},{"id":"2202.07304","title":"XAI for Transformers: Better Explanations through Conservative Propagation","created":"2022-02-15","cited_by_count":100,"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":"2311.02262","title":"Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs","created":"2023-11-03","cited_by_count":91,"area":null},{"id":"2404.00929","title":"A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias","created":"2024-04-01","cited_by_count":84,"area":null},{"id":"2106.14574","title":"Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics","created":"2021-06-28","cited_by_count":83,"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":"2103.01378","title":"Contrastive Explanations for Model Interpretability","created":"2021-03-02","cited_by_count":75,"area":null},{"id":"2106.11410","title":"A Survey of Race, Racism, and Anti-Racism in NLP","created":"2021-06-21","cited_by_count":75,"area":null},{"id":"2203.13928","title":"On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations","created":"2022-03-25","cited_by_count":75,"area":null},{"id":"2301.07255","title":"Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations","created":"2023-01-18","cited_by_count":73,"area":null},{"id":"2308.00755","title":"The Bias Amplification Paradox in Text-to-Image Generation","created":"2023-08-01","cited_by_count":70,"area":null},{"id":"2205.02526","title":"Theories of \"Gender\" in NLP Bias Research","created":"2022-05-05","cited_by_count":62,"area":null},{"id":"2110.13796","title":"Post-processing for Individual Fairness","created":"2021-10-26","cited_by_count":61,"area":null},{"id":"2101.05303","title":"Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making","created":"2021-01-13","cited_by_count":58,"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":"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":"2104.15135","title":"Explanation-Based Human Debugging of NLP Models: A Survey","created":"2021-04-30","cited_by_count":53,"area":null},{"id":"2205.12586","title":"Perturbation Augmentation for Fairer NLP","created":"2022-05-25","cited_by_count":52,"area":null},{"id":"2211.01528","title":"Fair and Optimal Classification via Post-Processing","created":"2022-11-03","cited_by_count":51,"area":null},{"id":"2402.09631","title":"Representation Surgery: Theory and Practice of Affine Steering","created":"2024-02-15","cited_by_count":50,"area":null},{"id":"2402.11190","title":"Disclosure and Mitigation of Gender Bias in LLMs","created":"2024-02-17","cited_by_count":49,"area":null},{"id":"2101.10001","title":"Diverse Adversaries for Mitigating Bias in Training","created":"2021-01-25","cited_by_count":48,"area":null},{"id":"2201.12191","title":"Kernelized Concept Erasure","created":"2022-01-28","cited_by_count":48,"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":"2103.12279","title":"SelfExplain: A Self-Explaining Architecture for Neural Text Classifiers","created":"2021-03-23","cited_by_count":44,"area":null},{"id":"2402.12649","title":"Bias in Language Models: Beyond Trick Tests and Toward RUTEd Evaluation","created":"2024-02-20","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":"2404.02062","title":"Digital Forgetting in Large Language Models: A Survey of Unlearning Methods","created":"2024-04-02","cited_by_count":40,"area":"safety"},{"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":"2203.11852","title":"Representation Bias in Data: A Survey on Identification and Resolution Techniques","created":"2022-03-22","cited_by_count":37,"area":null},{"id":"2104.13640","title":"Societal Biases in Retrieved Contents: Measurement Framework and Adversarial Mitigation for BERT Rankers","created":"2021-04-28","cited_by_count":35,"area":null},{"id":"2109.08253","title":"Balancing out Bias: Achieving Fairness Through Balanced Training","created":"2021-09-16","cited_by_count":34,"area":null},{"id":"2109.10645","title":"Contrastive Learning for Fair Representations","created":"2021-09-22","cited_by_count":34,"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":"2306.00966","title":"The Hidden Language of Diffusion Models","created":"2023-06-01","cited_by_count":34,"area":"diffusion"},{"id":"2107.02233","title":"End-to-End Weak Supervision","created":"2021-07-05","cited_by_count":33,"area":null},{"id":"2206.09860","title":"Fewer Errors, but More Stereotypes? The Effect of Model Size on Gender Bias","created":"2022-06-20","cited_by_count":33,"area":null},{"id":"2302.10908","title":"Human-Centric Multimodal Machine Learning: Recent Advances and Testbed on AI-based Recruitment","created":"2023-02-13","cited_by_count":33,"area":null},{"id":"2406.12232","title":"\"You Gotta be a Doctor, Lin\": An Investigation of Name-Based Bias of Large Language Models in Employment Recommendations","created":"2024-06-18","cited_by_count":33,"area":null},{"id":"2108.05449","title":"Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimization","created":"2021-08-11","cited_by_count":32,"area":null},{"id":"2111.11665","title":"RadFusion: Benchmarking Performance and Fairness for Multimodal Pulmonary Embolism Detection from CT and EHR","created":"2021-11-23","cited_by_count":32,"area":null},{"id":"2106.01087","title":"Is Sparse Attention more Interpretable?","created":"2021-06-02","cited_by_count":31,"area":null},{"id":"2210.10040","title":"The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks","created":"2022-10-18","cited_by_count":31,"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":"2306.02080","title":"Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models","created":"2023-06-03","cited_by_count":31,"area":"mllm"},{"id":"2311.00306","title":"Probing Explicit and Implicit Gender Bias through LLM Conditional Text Generation","created":"2023-11-01","cited_by_count":31,"area":null},{"id":"2401.08495","title":"Large Language Models Portray Socially Subordinate Groups as More Homogeneous, Consistent with a Bias Observed in Humans","created":"2024-01-16","cited_by_count":31,"area":null},{"id":"2407.00600","title":"GenderBias-\\emph{VL}: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing","created":"2024-06-30","cited_by_count":31,"area":"mllm"},{"id":"2109.10441","title":"Evaluating Debiasing Techniques for Intersectional Biases","created":"2021-09-21","cited_by_count":30,"area":null},{"id":"2205.05126","title":"A Meta-Analysis of the Utility of Explainable Artificial Intelligence in Human-AI Decision-Making","created":"2022-05-10","cited_by_count":29,"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":"2204.12130","title":"LM-Debugger: An Interactive Tool for Inspection and Intervention in Transformer-Based Language Models","created":"2022-04-26","cited_by_count":28,"area":null},{"id":"2207.00938","title":"Interpretable by Design: Learning Predictors by Composing Interpretable Queries","created":"2022-07-03","cited_by_count":28,"area":null},{"id":"2306.08158","title":"Sociodemographic Bias in Language Models: A Survey and Forward Path","created":"2023-06-13","cited_by_count":28,"area":null},{"id":"2411.00997","title":"Identifying Implicit Social Biases in Vision-Language Models","created":"2024-11-01","cited_by_count":27,"area":"mllm"},{"id":"2401.10862","title":"Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning","created":"2024-01-19","cited_by_count":26,"area":"safety"},{"id":"2407.08188","title":"Position: Measure Dataset Diversity, Don't Just Claim It","created":"2024-07-11","cited_by_count":26,"area":null},{"id":"2209.11812","title":"Explanations, Fairness, and Appropriate Reliance in Human-AI Decision-Making","created":"2022-09-23","cited_by_count":25,"area":null},{"id":"2302.06321","title":"Parameter-efficient Modularised Bias Mitigation via AdapterFusion","created":"2023-02-13","cited_by_count":25,"area":null},{"id":"2302.06503","title":"Ground(less) Truth: A Causal Framework for Proxy Labels in Human-Algorithm Decision-Making","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":"2407.19200","title":"On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs","created":"2024-07-27","cited_by_count":25,"area":"mechinterp"},{"id":"2110.09253","title":"A Sociotechnical View of Algorithmic Fairness","created":"2021-09-27","cited_by_count":24,"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":"2109.03300","title":"Hi, my name is Martha: Using names to measure and mitigate bias in generative dialogue models","created":"2021-09-07","cited_by_count":23,"area":null},{"id":"2207.02159","title":"Robustness Analysis of Video-Language Models Against Visual and Language Perturbations","created":"2022-07-05","cited_by_count":23,"area":null},{"id":"2205.02393","title":"Optimising Equal Opportunity Fairness in Model Training","created":"2022-05-05","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":"2212.10563","title":"BLIND: Bias Removal With No Demographics","created":"2022-12-20","cited_by_count":22,"area":null},{"id":"2401.06408","title":"AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters","created":"2024-01-12","cited_by_count":22,"area":null},{"id":"2405.17159","title":"Stop! In the Name of Flaws: Disentangling Personal Names and Sociodemographic Attributes in NLP","created":"2024-05-27","cited_by_count":22,"area":null},{"id":"2406.08824","title":"LLM-Driven Robots Risk Enacting Discrimination, Violence, and Unlawful Actions","created":"2024-06-13","cited_by_count":22,"area":null},{"id":"2102.04256","title":"Problematic Machine Behavior: A Systematic Literature Review of Algorithm Audits","created":"2021-02-03","cited_by_count":21,"area":null},{"id":"2211.11109","title":"Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness","created":"2022-11-20","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":"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":"2112.07447","title":"Measuring Fairness with Biased Rulers: A Survey on Quantifying Biases in Pretrained Language Models","created":"2021-12-14","cited_by_count":20,"area":null},{"id":"2407.12858","title":"Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)","created":"2024-07-10","cited_by_count":20,"area":null},{"id":"2109.10444","title":"Fairness-aware Class Imbalanced Learning","created":"2021-09-21","cited_by_count":19,"area":null},{"id":"2202.01327","title":"Adaptive Sampling Strategies to Construct Equitable Training Datasets","created":"2022-01-31","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}],"next_cursor":"100"}