Ananth Balashankar

Google (United States) — United States

Computer Science · Physical Sciences

6h-index138citations34works0.22yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Topic Modeling(12), Adversarial Robustness in Machine Learning(7), Natural Language Processing Techniques(4), Sentiment Analysis and Opinion Mining(3), Ethics and Social Impacts of AI(3)

Publications34 total

Adversarial Reinforcement Learning for Large Language Model Agent Safety
arXiv (Cornell University)·2025Open Access
FieldFormer: Physics-Informed Transformers for Spatio-Temporal Field Reconstruction from Sparse Sensors
arXiv (Cornell University)·2025Open Access
Comprehensive Monitoring of Air Pollution Hotspots Using Sparse Sensor Networks
ACM Journal on Computing and Sustainable Societies·2025· 2 citedOpen Access
InfAlign: Inference-aware language model alignment
arXiv (Cornell University)·2024Open Access
Comprehensive Monitoring of Air Pollution Hotspots Using Sparse Sensor Networks
arXiv (Cornell University)·2024Open Access
Inducing Group Fairness in Prompt-Based Language Model Decisions
arXiv (Cornell University)·2024Open Access
Automated Adversarial Discovery for Safety Classifiers
arXiv (Cornell University)·2024Open Access
Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment
arXiv (Cornell University)·2024Open Access
Automated Adversarial Discovery for Safety Classifiers
2024Open Access
Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment
2024Open Access
Improving Few-shot Generalization of Safety Classifiers via Data Augmented Parameter-Efficient Fine-Tuning
arXiv (Cornell University)·2023Open Access
Break it, Imitate it, Fix it: Robustness by Generating Human-Like Attacks
arXiv (Cornell University)·2023Open Access
Improving Classifier Robustness through Active Generation of Pairwise Counterfactuals
arXiv (Cornell University)·2023Open Access
Predicting food crises using news streams
Science Advances·2023· 24 citedOpen Access
Effective Robustness against Natural Distribution Shifts for Models with Different Training Data
arXiv (Cornell University)·2023Open Access
Improving Classifier Robustness through Active Generative Counterfactual Data Augmentation
2023· 1 citedOpen Access
Beyond The Text: Analysis of Privacy Statements through Syntactic and Semantic Role Labeling
2023· 1 citedOpen Access
Modeling fine-grained spatio-temporal pollution maps with low-cost sensors
npj Climate and Atmospheric Science·2022· 15 citedOpen Access
Targeted Policy Recommendations using Outcome-aware Clustering
2022· 1 cited
The Need for Transparent Demographic Group Trade-Offs in Credit Risk and Income Classification
Lecture notes in computer science·2022· 2 cited
page 1 of 2Next →

Frequent Co-authors

Lakshminarayanan Subramanian(18), Alex Beutel(7), Yao Qin(6), Ahmad Beirami(6), Samuel P. Fraiberger(5), Aradhana Sinha(5), Thomas Wies(4), Alyssa Lees(4), Jilin Chen(4), Shiva R. Iyer(3), Nita Soans(3), Anant Sudarshan(3), Rohini Pande(3), Xuezhi Wang(3), Ben Packer(3), Nithum Thain(3), Ed H.(3), Ankit Bhardwaj(3), Preethi Lahoti(3), Jacob Eisenstein(3)