Artificial Intelligence › Core AI ›

Fairness

1139 directly classified papers

Papers per year

Papers

This prompt is measuring <mask>: evaluating bias evaluation in language models ACL 2023

Debiasing should be Good and Bad: Measuring the Consistency of Debiasing Techniques in Language Models ACL 2023

A Multi-modal Debiasing Model with Dynamical Constraint for Robust Visual Question Answering ACL 2023

Mind the Biases: Quantifying Cognitive Biases in Language Model Prompting ACL 2023

Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projection ACL 2023

Unlearning Bias in Language Models by Partitioning Gradients ACL 2023

A Multi-dimensional study on Bias in Vision-Language models ACL 2023

Trade-Offs Between Fairness and Privacy in Language Modeling ACL 2023

Stereotypes and Smut: The (Mis)representation of Non-cisgender Identities by Text-to-Image Models ACL 2023

Stubborn Lexical Bias in Data and Models ACL 2023

CFL: Causally Fair Language Models Through Token-level Attribute Controlled Generation ACL 2023

Race, Gender, and Age Biases in Biomedical Masked Language Models ACL 2023

Gender-Inclusive Grammatical Error Correction through Augmentation ACL 2023

UnedMediaBiasTeam @ SemEval-2023 Task 3: Can We Detect Persuasive Techniques Transferring Knowledge From Media Bias Detection? ACL 2023

xiacui at SemEval-2023 Task 11: Learning a Model in Mixed-Annotator Datasets Using Annotator Ranking Scores as Training Weights ACL 2023

LEXPLAIN: Improving Model Explanations via Lexicon Supervision ACL 2023

Automated Ableism: An Exploration of Explicit Disability Biases in Sentiment and Toxicity Analysis Models ACL 2023

An Empirical Study of Metrics to Measure Representational Harms in Pre-Trained Language Models ACL 2023

Debunking Biases in Attention ACL 2023

Multilingual Language Models are not Multicultural: A Case Study in Emotion ACL 2023

DeTexD: A Benchmark Dataset for Delicate Text Detection ACL 2023

BiasX: “Thinking Slow” in Toxic Content Moderation with Explanations of Implied Social Biases EMNLP 2023

On the Challenges of Using Black-Box APIs for Toxicity Evaluation in Research EMNLP 2023

Gender Biases in Automatic Evaluation Metrics for Image Captioning EMNLP 2023

Towards Conceptualization of “Fair Explanation”: Disparate Impacts of anti-Asian Hate Speech Explanations on Content Moderators EMNLP 2023