← Learning Types
Machine Learning › Learning Types ›

Fairness

796 directly classified papers

Papers per year

Papers

Reducing Sensitivity on Speaker Names for Text Generation from Dialogues ACL 2023
Risks and NLP Design: A Case Study on Procedural Document QA ACL 2023
Fair yet Asymptotically Equal Collaborative Learning ICML 2023
Stubborn Lexical Bias in Data and Models ACL 2023
SeeGULL: A Stereotype Benchmark with Broad Geo-Cultural Coverage Leveraging Generative Models ACL 2023
Causal Intervention for Mitigating Name Bias in Machine Reading Comprehension ACL 2023
Does BERT Exacerbate Gender or L1 Biases in Automated English Speaking Assessment? ACL 2023
When Do Annotator Demographics Matter? Measuring the Influence of Annotator Demographics with the POPQUORN Dataset ACL 2023
Are Fairy Tales Fair? Analyzing Gender Bias in Temporal Narrative Event Chains of Children’s Fairy Tales ACL 2023
FAIRER: Fairness as Decision Rationale Alignment ICML 2023
Towards Stable Natural Language Understanding via Information Entropy Guided Debiasing ACL 2023
Loss Balancing for Fair Supervised Learning ICML 2023
Targeted Data Generation: Finding and Fixing Model Weaknesses ACL 2023
Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation ICML 2023
FARE: Provably Fair Representation Learning with Practical Certificates ICML 2023
Understanding the Impact of Adversarial Robustness on Accuracy Disparity ICML 2023
Fair and Accurate Decision Making through Group-Aware Learning ICML 2023
On Generalized Degree Fairness in Graph Neural Networks AAAI 2023
BLIND: Bias Removal With No Demographics ACL 2023
Multicalibration as Boosting for Regression ICML 2023
Generalized Disparate Impact for Configurable Fairness Solutions in ML ICML 2023
On the Impact of Algorithmic Recourse on Social Segregation ICML 2023
Attribution-based Explanations that Provide Recourse Cannot be Robust JMLR 2023
Certified Robust Neural Networks: Generalization and Corruption Resistance ICML 2023
Individually Fair Learning with One-Sided Feedback ICML 2023