Preethi Lahoti
5 papers · 2020–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Conference Polyglot
(4)
π
Interdisciplinary Bridge
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π
Cross-Pollinator
(15)
Conferences
EMNLP (2)
ICML (1)
NAACL (1)
NIPS (1)
Top co-authors
Keywords
large language model
(2)
adversarial learning
(2)
prompt engineering
(1)
toxicity detection
(1)
machine learning
(1)
adversarial attack
(1)
group fairness
(1)
safety evaluation
(1)
adversarial testing
(1)
demographic parity
(1)
data generation
(1)
prompting technique
(1)
adversarial reweighting
(1)
safety classifier
(1)
worst-case fairness
(1)
demographic representation
(1)
collective critique
(1)
rawlsian max-min fairness
(1)
domain adaptation
(1)
Papers
FRAPPΓ: A Group Fairness Framework for Post-Processing Everything
ICML 2024
Automated Adversarial Discovery for Safety Classifiers
NAACL 2024
Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Voting
EMNLP 2023
AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications
EMNLP 2023
Fairness without Demographics through Adversarially Reweighted Learning
NIPS 2020