Ananth Balashankar

Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment

Beyond The Text: Analysis of Privacy Statements through Syntactic and Semantic Role Labeling

Improving Classifier Robustness through Active Generative Counterfactual Data Augmentation

Effective Robustness against Natural Distribution Shifts for Models with Different Training Data

Improving Few-shot Generalization of Safety Classifiers via Data Augmented Parameter-Efficient Fine-Tuning

Break it, Imitate it, Fix it: Robustness by Generating Human-Like Attacks

Discovering Localized Pollution Hotspots Using Sparse Sensor Measurements

Learning Conditional Granger Causal Temporal Networks