Piotr Mardziel
4 papers · 2020–2021 · 3 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
(10)
Venues
Top co-authors
Research topics
Keywords
information theory
(1)
algorithmic fairness
(1)
model robustness
(1)
attention mechanism
(1)
neural network interpretability
(1)
feature attribution
(1)
lipschitz continuity
(1)
adversarial attack
(1)
recurrent neural network
(1)
language model
(1)
partial information decomposition
(1)
counterfactual reasoning
(1)
counterfactual fairness
(1)
causal analysis
(1)
information flow
(1)
syntactic structure
(1)
lstm language model
(1)
subject-verb agreement
(1)
gradient-based attribution
(1)
influence path
(1)
Papers
Influence Patterns for Explaining Information Flow in BERT
NeurIPS 2021
An Information-Theoretic Quantification of Discrimination with Exempt Features
AAAI 2020
Influence Paths for Characterizing Subject-Verb Number Agreement in LSTM Language Models
ACL 2020
Smoothed Geometry for Robust Attribution
NeurIPS 2020