swetasudha panda
4 papers · 2018–2022 · 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
🗺️
Taxonomy Completionist
(11)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
reinforcement learning
(1)
semi-supervised learning
(1)
function approximation
(1)
posterior regularization
(1)
bias mitigation
(1)
pre-trained model
(1)
toxicity classification
(1)
stackelberg game
(1)
pre-trained language model
(1)
label bia
(1)
factored mdp
(1)
social bia
(1)
state interdiction
(1)
bayesian interdiction
(1)
model fairness
(1)
dataset quality
(1)
harmful stereotype
(1)
bias transfer
(1)
social bias mitigation
(1)
fairness in machine learning
(1)
Papers
Don’t Just Clean It, Proxy Clean It: Mitigating Bias by Proxy in Pre-Trained Models
EMNLP 2022
Upstream Mitigation Is Not All You Need: Testing the Bias Transfer Hypothesis in Pre-Trained Language Models
ACL 2022
Unlocking Fairness: a Trade-off Revisited
NeurIPS 2019
Scalable Initial State Interdiction for Factored MDPs
IJCAI 2018