Mamta
5 papers · 2022–2025 · 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
(12)
Research topics
Keywords
sentiment classification
(2)
adversarial robustness
(2)
fact verification
(1)
masked language model
(1)
toxicity detection
(1)
code-mixed text
(1)
model interpretability
(1)
toxic content detection
(1)
parameter optimization
(1)
adversarial defense
(1)
bias mitigation
(1)
shapley value
(1)
text perturbation
(1)
adversarial sample
(1)
model explainability
(1)
phonetic feature
(1)
masked language modelling
(1)
large language model
(1)
neural network pruning
(1)
transformer model
(1)
Papers
FactEval: Evaluating the Robustness of Fact Verification Systems in the Era of Large Language Models
NAACL 2025
I-GUARD: Interpretability-Guided Parameter Optimization for Adversarial Defense
EMNLP 2025
BiasWipe: Mitigating Unintended Bias in Text Classifiers through Model Interpretability
EMNLP 2024
Elevating Code-mixed Text Handling through Auditory Information of Words
EMNLP 2023
Adversarial Sample Generation for Aspect based Sentiment Classification
AACL 2022