Artificial Intelligence › Core AI ›

Responsible AI

1991 directly classified papers

Papers per year

Papers

Debiasing Isn’t Enough! – on the Effectiveness of Debiasing MLMs and Their Social Biases in Downstream Tasks COLING 2022

A Study of Implicit Bias in Pretrained Language Models against People with Disabilities COLING 2022

Fairness Interventions as (Dis)Incentives for Strategic Manipulation ICML 2022

Text Simplification of College Admissions Instructions: A Professionally Simplified and Verified Corpus COLING 2022

TruthfulQA: Measuring How Models Mimic Human Falsehoods ACL 2022

Should We Ban English NLP for a Year? EMNLP 2022

FairLib: A Unified Framework for Assessing and Improving Fairness EMNLP 2022

Open-domain Dialogue Generation: What We Can Do, Cannot Do, And Should Do Next ACL 2022

Intrinsic Bias Metrics Do Not Correlate with Application Bias IJCNLP 2021

Beyond Fair Pay: Ethical Implications of NLP Crowdsourcing NAACL 2021

Membership Inference Attacks on Deep Regression Models for Neuroimaging MIDL 2021

Improving Factual Consistency Between a Response and Persona Facts EACL 2021

A Study of Automatic Metrics for the Evaluation of Natural Language Explanations EACL 2021

Case Study: Deontological Ethics in NLP NAACL 2021

Responsible Prediction Making of COVID-19 Mortality (Student Abstract) AAAI 2021

Let-Mi: An Arabic Levantine Twitter Dataset for Misogynistic Language EACL 2021

Human-in-the-Loop for Data Collection: a Multi-Target Counter Narrative Dataset to Fight Online Hate Speech ACL 2021

Intrinsic Bias Metrics Do Not Correlate with Application Bias ACL 2021

The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation EMNLP 2021

Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets NIPS 2021

Profanity-Avoiding Training Framework for Seq2seq Models with Certified Robustness EMNLP 2021

An Overview of Fairness in Data – Illuminating the Bias in Data Pipeline EACL 2021

HULK: An Energy Efficiency Benchmark Platform for Responsible Natural Language Processing EACL 2021

Machine Translationese: Effects of Algorithmic Bias on Linguistic Complexity in Machine Translation EACL 2021

Through the Looking Glass: Learning to Attribute Synthetic Text Generated by Language Models EACL 2021