Ananth Balashankar

38 papers A* 4A 1C 2Misc 1Journal 21Unranked 8

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Noisy but Valid: Robust Statistical Evaluation of LLMs with Imperfect Judges. CoRR Chen Feng, Minghe shen, Ananth Balashankar, Carsten Gerner-Beuerle, Miguel R. D. Rodrigues
2026	J	`jnl`	Systematic Scaling Analysis of Jailbreak Attacks in Large Language Models. CoRR Xiangwen Wang, Ananth Balashankar, Varun Chandrasekaran
2025	J	`jnl`	Adversarial Reinforcement Learning for Large Language Model Agent Safety. CoRR Zizhao Wang, Dingcheng Li, Vaishakh Keshava, Phillip Wallis, Ananth Balashankar, Peter Stone, Lukas Rutishauser
2025	J	`jnl`	BEFT: Bias-Efficient Fine-Tuning of Language Models. CoRR Baichuan Huang, Ananth Balashankar, Amir Aminifar
2025	J	`jnl`	Breaking the Illusion: Consensus-Based Generative Mitigation of Adversarial Illusions in Multi-Modal Embeddings. CoRR Fatemeh Akbarian, Anahita Baninajjar, Yingyi Zhang, Ananth Balashankar, Amir Aminifar
2025	J	`jnl`	Comprehensive Monitoring of Air Pollution Hotspots Using Sparse Sensor Networks. ACM J. Comput. Sustain. Soc. Ankit Bhardwaj, Ananth Balashankar, Shiva R. Iyer, Nita Soans, Anant Sudarshan, Rohini Pande, Lakshminarayanan Subramanian
2025	J	`jnl`	FieldFormer: Physics-Informed Transformers for Spatio-Temporal Field Reconstruction from Sparse Sensors. CoRR Ankit Bhardwaj, Ananth Balashankar, Lakshminarayanan Subramanian
2025	A*	`conf`	InfAlign: Inference-aware language model alignment. ICML Ananth Balashankar, Ziteng Sun, Jonathan Berant, Jacob Eisenstein, Michael Collins, Adrian Hutter, Jong Lee, Chirag Nagpal, Flavien Prost, Aradhana Sinha, Ananda Theertha Suresh, Ahmad Beirami
2024	J	`jnl`	Automated Adversarial Discovery for Safety Classifiers. CoRR Yash Kumar Lal, Preethi Lahoti, Aradhana Sinha, Yao Qin, Ananth Balashankar
2024	J	`jnl`	Break it, Imitate it, Fix it: Robustness by Generating Human-Like Attacks. Trans. Mach. Learn. Res. Aradhana Sinha, Ananth Balashankar, Ahmad Beirami, Thi Avrahami, Jilin Chen, Alex Beutel
2024	J	`jnl`	Discovering Hidden Pollution Hotspots Using Sparse Sensor Measurements. CoRR Ankit Bhardwaj, Ananth Balashankar, Shiva R. Iyer, Nita Soans, Anant Sudarshan, Rohini Pande, Lakshminarayanan Subramanian
2024	J	`jnl`	Inducing Group Fairness in LLM-Based Decisions. CoRR James Atwood, Preethi Lahoti, Ananth Balashankar, Flavien Prost, Ahmad Beirami
2024	J	`jnl`	InfAlign: Inference-aware language model alignment. CoRR Ananth Balashankar, Ziteng Sun, Jonathan Berant, Jacob Eisenstein, Michael Collins, Adrian Hutter, Jong Lee, Chirag Nagpal, Flavien Prost, Aradhana Sinha, Ananda Theertha Suresh, Ahmad Beirami
2024	A*	`conf`	Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment. EMNLP Zhaofeng Wu, Ananth Balashankar, Yoon Kim, Jacob Eisenstein, Ahmad Beirami
2024	J	`jnl`	Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment. CoRR Zhaofeng Wu, Ananth Balashankar, Yoon Kim, Jacob Eisenstein, Ahmad Beirami
2023	J	`jnl`	Break it, Imitate it, Fix it: Robustness by Generating Human-Like Attacks. CoRR Aradhana Sinha, Ananth Balashankar, Ahmad Beirami, Thi Avrahami, Jilin Chen, Alex Beutel
2023	A*	`conf`	Effective Robustness against Natural Distribution Shifts for Models with Different Training Data. NeurIPS Zhouxing Shi, Nicholas Carlini, Ananth Balashankar, Ludwig Schmidt, Cho-Jui Hsieh, Alex Beutel, Yao Qin
2023	J	`jnl`	Effective Robustness against Natural Distribution Shifts for Models with Different Training Data. CoRR Zhouxing Shi, Nicholas Carlini, Ananth Balashankar, Ludwig Schmidt, Cho-Jui Hsieh, Alex Beutel, Yao Qin
2023	J	`jnl`	Improving Classifier Robustness through Active Generation of Pairwise Counterfactuals. CoRR Ananth Balashankar, Xuezhi Wang, Yao Qin, Ben Packer, Nithum Thain, Jilin Chen, Ed H. Chi, Alex Beutel
2023	—	`conf`	Improving Classifier Robustness through Active Generative Counterfactual Data Augmentation. EMNLP (Findings) Ananth Balashankar, Xuezhi Wang, Yao Qin, Ben Packer, Nithum Thain, Ed H. Chi, Jilin Chen, Alex Beutel
2023	J	`jnl`	Improving Few-shot Generalization of Safety Classifiers via Data Augmented Parameter-Efficient Fine-Tuning. CoRR Ananth Balashankar, Xiao Ma, Aradhana Sinha, Ahmad Beirami, Yao Qin, Jilin Chen, Alex Beutel
2023	—	`conf`	Learning Conditional Granger Causal Temporal Networks. CLeaR Ananth Balashankar, Srikanth Jagabathula, Lakshmi Subramanian
2022	—	`—`	Enhancing Robustness through Domain Faithful Deep Learning Systems Ananth Balashankar
2022	C	`conf`	Targeted Policy Recommendations using Outcome-aware Clustering. COMPASS Ananth Balashankar, Samuel Fraiberger, Eric Deregt, Marelize Gorgens, Lakshminarayanan Subramanian
2022	—	`conf`	The Need for Transparent Demographic Group Trade-Offs in Credit Risk and Income Classification. iConference (1) Ananth Balashankar, Alyssa Lees
2021	—	`conf`	Can We Improve Model Robustness through Secondary Attribute Counterfactuals? EMNLP (1) Ananth Balashankar, Xuezhi Wang, Ben Packer, Nithum Thain, Ed H. Chi, Alex Beutel
2021	A	`conf`	Enhancing Neural Recommender Models through Domain-Specific Concordance. WSDM Ananth Balashankar, Alex Beutel, Lakshminarayanan Subramanian
2021	J	`jnl`	Fine-grained prediction of food insecurity using news streams. CoRR Ananth Balashankar, Lakshminarayanan Subramanian, Samuel P. Fraiberger
2021	—	`conf`	Learning Faithful Representations of Causal Graphs. ACL/IJCNLP (1) Ananth Balashankar, Lakshminarayanan Subramanian
2020	J	`jnl`	Beyond The Text: Analysis of Privacy Statements through Syntactic and Semantic Role Labeling. CoRR Yan Shvartzshnaider, Ananth Balashankar, Vikas Patidar, Thomas Wies, Lakshminarayanan Subramanian
2019	J	`jnl`	Fairness Sample Complexity and the Case for Human Intervention. CoRR Ananth Balashankar, Alyssa Lees
2019	—	`conf`	Identifying Predictive Causal Factors from News Streams. EMNLP/IJCNLP (1) Ananth Balashankar, Sunandan Chakraborty, Samuel Fraiberger, Lakshminarayanan Subramanian
2019	C	`conf`	Reconstructing the MERS disease outbreak from news. COMPASS Ananth Balashankar, Aashish Dugar, Lakshminarayanan Subramanian, Samuel Fraiberger
2019	A*	`conf`	VACCINE: Using Contextual Integrity For Data Leakage Detection. WWW Yan Shvartzshnaider, Zvonimir Pavlinovic, Ananth Balashankar, Thomas Wies, Lakshminarayanan Subramanian, Helen Nissenbaum, Prateek Mittal
2019	J	`jnl`	What is Fair? Exploring Pareto-Efficiency for Fairness Constrained Classifiers. CoRR Ananth Balashankar, Alyssa Lees, Chris Welty, Lakshminarayanan Subramanian
2018	—	`conf`	RECIPE: Applying Open Domain Question Answering to Privacy Policies. QA@ACL Yan Shvartzshanider, Ananth Balashankar, Thomas Wies, Lakshminarayanan Subramanian
2018	—	`conf`	Unsupervised Word Influencer Networks from News Streams. ECONLP@ACL Ananth Balashankar, Sunandan Chakraborty, Lakshminarayanan Subramanian
2014	Misc	`conf`	(Stable) virtual landmarks: Spatial dropbox to enhance retail experience. COMSNETS Swadhin Pradhan, Ananth Balashankar, Niloy Ganguly, Bivas Mitra