{"total":65,"rows":[{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786,"area":null},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382,"area":null},{"id":"2306.01943","title":"NLPositionality: Characterizing Design Biases of Datasets and Models","created":"2023-06-02","cited_by_count":94,"area":null},{"id":"2210.07700","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","created":"2022-10-14","cited_by_count":80,"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":"2209.03942","title":"Data Feedback Loops: Model-driven Amplification of Dataset Biases","created":"2022-09-08","cited_by_count":60,"area":null},{"id":"2508.01491","title":"The Homogenizing Effect of Large Language Models on Human Expression and Thought","created":"2025-08-02","cited_by_count":35,"area":"lr"},{"id":"2301.11100","title":"Vision-Language Models Performing Zero-Shot Tasks Exhibit Gender-based Disparities","created":"2023-01-26","cited_by_count":31,"area":"mllm"},{"id":"2403.01189","title":"Training Unbiased Diffusion Models From Biased Dataset","created":"2024-03-02","cited_by_count":25,"area":"diffusion"},{"id":"2310.05055","title":"FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis","created":"2023-10-08","cited_by_count":23,"area":null},{"id":"2210.11924","title":"Men Also Do Laundry: Multi-Attribute Bias Amplification","created":"2022-10-21","cited_by_count":21,"area":null},{"id":"2303.11477","title":"NASDM: Nuclei-Aware Semantic Histopathology Image Generation Using Diffusion Models","created":"2023-03-20","cited_by_count":18,"area":"diffusion"},{"id":"2304.03693","title":"Model-Agnostic Gender Debiased Image Captioning","created":"2023-04-07","cited_by_count":17,"area":null},{"id":"2305.16636","title":"DataFinder: Scientific Dataset Recommendation from Natural Language Descriptions","created":"2023-05-26","cited_by_count":15,"area":null},{"id":"2402.01787","title":"Harm Amplification in Text-to-Image Models","created":"2024-02-01","cited_by_count":15,"area":null},{"id":"2402.01909","title":"On Catastrophic Inheritance of Large Foundation Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2312.11803","title":"NLP for Maternal Healthcare: Perspectives and Guiding Principles in the Age of LLMs","created":"2023-12-19","cited_by_count":14,"area":null},{"id":"2304.10819","title":"Auditing and Generating Synthetic Data with Controllable Trust Trade-offs","created":"2023-04-21","cited_by_count":13,"area":null},{"id":"2305.14970","title":"Getting Sick After Seeing a Doctor? Diagnosing and Mitigating Knowledge Conflicts in Event Temporal Reasoning","created":"2023-05-24","cited_by_count":13,"area":"lr"},{"id":"2405.21070","title":"What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights","created":"2024-05-31","cited_by_count":13,"area":null},{"id":"2501.09687","title":"U-Fair: Uncertainty-based Multimodal Multitask Learning for Fairer Depression Detection","created":"2025-01-16","cited_by_count":12,"area":null},{"id":"2212.06641","title":"Simplicity Bias Leads to Amplified Performance Disparities","created":"2022-12-13","cited_by_count":11,"area":null},{"id":"2506.06166","title":"The Lock-in Hypothesis: Stagnation by Algorithm","created":"2025-06-06","cited_by_count":11,"area":null},{"id":"2405.08027","title":"Automating Data Annotation under Strategic Human Agents: Risks and Potential Solutions","created":"2024-05-12","cited_by_count":9,"area":null},{"id":"2405.20494","title":"Slight Corruption in Pre-training Data Makes Better Diffusion Models","created":"2024-05-30","cited_by_count":9,"area":"diffusion"},{"id":"2310.02533","title":"Quantifying and mitigating the impact of label errors on model disparity metrics","created":"2023-10-04","cited_by_count":7,"area":null},{"id":"2310.17530","title":"Evaluating Bias and Fairness in Gender-Neutral Pretrained Vision-and-Language Models","created":"2023-10-26","cited_by_count":6,"area":null},{"id":"2502.07957","title":"Intrinsic Bias is Predicted by Pretraining Data and Correlates with Downstream Performance in Vision-Language Encoders","created":"2025-02-11","cited_by_count":6,"area":"mllm"},{"id":"2508.15831","title":"Who's Asking? Investigating Bias Through the Lens of Disability Framed Queries in LLMs","created":"2025-08-18","cited_by_count":6,"area":null},{"id":"2302.08572","title":"Towards Reliable Assessments of Demographic Disparities in Multi-Label Image Classifiers","created":"2023-02-16","cited_by_count":5,"area":null},{"id":"2406.17385","title":"Native Design Bias: Studying the Impact of English Nativeness on Language Model Performance","created":"2024-06-25","cited_by_count":5,"area":null},{"id":"2307.07331","title":"How Different Is Stereotypical Bias Across Languages?","created":"2023-07-14","cited_by_count":4,"area":null},{"id":"2405.16762","title":"Addressing Discretization-Induced Bias in Demographic Prediction","created":"2024-05-27","cited_by_count":4,"area":null},{"id":"2408.01959","title":"Dataset Scale and Societal Consistency Mediate Facial Impression Bias in Vision-Language AI","created":"2024-08-04","cited_by_count":4,"area":"diffusion"},{"id":"2408.11448","title":"Lookism: The overlooked bias in computer vision","created":"2024-08-21","cited_by_count":4,"area":null},{"id":"2409.04188","title":"Reassessing the Validity of Spurious Correlations Benchmarks","created":"2024-09-06","cited_by_count":4,"area":null},{"id":"2411.10588","title":"A dataset of questions on decision-theoretic reasoning in Newcomb-like problems","created":"2024-11-15","cited_by_count":4,"area":"lr"},{"id":"2304.09826","title":"Fairness in AI and Its Long-Term Implications on Society","created":"2023-04-16","cited_by_count":3,"area":null},{"id":"2405.05031","title":"Mitigating Bias Using Model-Agnostic Data Attribution","created":"2024-05-08","cited_by_count":3,"area":null},{"id":"2507.07820","title":"AI Should Sense Better, Not Just Scale Bigger: Adaptive Sensing as a Paradigm Shift","created":"2025-07-10","cited_by_count":3,"area":null},{"id":"2606.06533","title":"Position: Don't Just \"Fix it in Post\": A Science of AI Must Study Training Dynamics","created":"2026-06-03","cited_by_count":3,"area":null},{"id":"2206.03226","title":"Fairness and Explainability in Automatic Decision-Making Systems. A challenge for computer science and law","created":"2022-05-14","cited_by_count":2,"area":null},{"id":"2506.11025","title":"When Algorithms Play Favorites: Lookism in the Generation and Perception of Faces","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2511.00177","title":"Can SAEs reveal and mitigate racial biases of LLMs in healthcare?","created":"2025-10-31","cited_by_count":2,"area":"mechinterp"},{"id":"2601.11651","title":"Aesthetics as Structural Harm: Algorithmic Lookism Across Text-to-Image Generation and Classification","created":"2026-01-15","cited_by_count":2,"area":null},{"id":"2312.15247","title":"Prompt-Propose-Verify: A Reliable Hand-Object-Interaction Data Generation Framework using Foundational Models","created":"2023-12-23","cited_by_count":1,"area":"diffusion"},{"id":"2412.04025","title":"Exploring the Influence of Label Aggregation on Minority Voices: Implications for Dataset Bias and Model Training","created":"2024-12-05","cited_by_count":1,"area":null},{"id":"2505.13122","title":"When majority rules, minority loses: bias amplification of gradient descent","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2506.09630","title":"In-Context Bias Propagation in LLM-Based Tabular Data Generation","created":"2025-06-11","cited_by_count":1,"area":null},{"id":"2509.12652","title":"Don't Change My View: Ideological Bias Auditing in Large Language Models","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2604.19984","title":"Bias in the Tails: How Name-conditioned Evaluative Framing in Resume Summaries Destabilizes LLM-based Hiring","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2301.07639","title":"A Comparative Analysis of Bias Amplification in Graph Neural Network Approaches for Recommender Systems","created":"2023-01-18","cited_by_count":0,"area":null},{"id":"2303.11449","title":"Bias mitigation techniques in image classification: fair machine learning in human heritage collections","created":"2023-03-20","cited_by_count":0,"area":null},{"id":"2303.16564","title":"Implicit Visual Bias Mitigation by Posterior Estimate Sharpening of a Bayesian Neural Network","created":"2023-03-29","cited_by_count":0,"area":null},{"id":"2307.08199","title":"Unbiased Image Synthesis via Manifold Guidance in Diffusion Models","created":"2023-07-17","cited_by_count":0,"area":"diffusion"},{"id":"2307.12935","title":"Rule By Example: Harnessing Logical Rules for Explainable Hate Speech Detection","created":"2023-07-24","cited_by_count":0,"area":null},{"id":"2401.02183","title":"FairGridSearch: A Framework to Compare Fairness-Enhancing Models","created":"2024-01-04","cited_by_count":0,"area":null},{"id":"2411.15051","title":"Fantastic Biases (What are They) and Where to Find Them","created":"2024-11-22","cited_by_count":0,"area":null},{"id":"2506.09106","title":"Bias Analysis in Unconditional Image Generative Models","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2509.26275","title":"Wasserstein Distributionally Robust Optimization Through the Lens of Structural Causal Models and Individual Fairness","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2511.13753","title":"Robustness of LLM-enabled vehicle trajectory prediction under data security threats","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2602.22470","title":"Beyond performance-wise Contribution Evaluation in Federated Learning","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2605.28137","title":"No Safe Dose: How Training Data Drives Unsafe Image Generation","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.14460","title":"A Computational Audit of Demographic Association Encoding in ClinicalBERT Language Predictions","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.16195","title":"Rater State Bias in RLHF Preference Data: An Audit Framework","created":"2026-04-14","cited_by_count":0,"area":"alignment"}],"next_cursor":null}