Preethi Lahoti
5 papers · 2020–2024 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
large language model
(2)
group fairness
(2)
adversarial learning
(2)
toxicity detection
(1)
machine learning
(1)
adversarial attack
(1)
safety evaluation
(1)
adversarial testing
(1)
demographic parity
(1)
regularized method
(1)
prediction model
(1)
data generation
(1)
prompting technique
(1)
adversarial reweighting
(1)
safety classifier
(1)
worst-case fairness
(1)
demographic representation
(1)
post processing
(1)
fairness mitigation
(1)
collective critique
(1)
Papers
Automated Adversarial Discovery for Safety Classifiers
NAACL 2024
FRAPPÉ: A Group Fairness Framework for Post-Processing Everything
ICML 2024
AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications
EMNLP 2023
Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Voting
EMNLP 2023
Fairness without Demographics through Adversarially Reweighted Learning
NeurIPS 2020