🧑‍🔬 Aditi Raghunathan — all works

29 works · ← Aditi Raghunathan

1. Certified Defenses against Adversarial Examples ↗arXiv (Cornell University) · no summary yetAditi Raghunathan, Jacob Steinhardt, Percy Liang2018 · 550 citations
2. Certified Robustness to Adversarial Word SubstitutionsConference on Empirical Methods in Natural Language Processing (EMNLP)Robin Jia, Aditi Raghunathan, Kerem Göksel, et al.2019 · 340 citations
3. An Explanation of In-context Learning as Implicit Bayesian InferencearXiv:2111.02080Sang Michael Xie, Aditi Raghunathan, Percy Liang, et al.2021 · 286 citations
4. Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution ↗arXiv (Cornell University) · no summary yetAnanya Kumar et al.2022 · 248 citations
5. Semidefinite relaxations for certifying robustness to adversarial examples ↗arXiv (Cornell University) · no summary yetAditi Raghunathan, Jacob Steinhardt, Percy Liang2018 · 201 citations
6. An Investigation of Why Overparameterization Exacerbates Spurious Correlations ↗arXiv (Cornell University) · no summary yetShiori Sagawa et al.2020 · 147 citations
7. Adversarial Training Can Hurt Generalization ↗arXiv (Cornell University) · no summary yetAditi Raghunathan et al.2019 · 139 citations
8. Robust Encodings: A Framework for Combating Adversarial Typos ↗Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · no summary yetErik Jones et al.2020 · 126 citations
9. Just Train Twice: Improving Group Robustness without Training Group Information ↗arXiv (Cornell University) · no summary yetEvan Zheran Liu et al.2021 · 125 citations
10. Unlabeled Data Improves Adversarial Robustness ↗arXiv (Cornell University) · no summary yetYair Carmon et al.2019 · 91 citations
11. Automatically Auditing Large Language Models via Discrete OptimizationarXiv:2303.04381Erik Jones, Anca Dragan, Aditi Raghunathan, et al.2023 · 89 citations
12. Repetition Improves Language Model EmbeddingsarXiv:2402.15449Jacob Mitchell Springer, Suhas Kotha, Daniel Fried, et al.2024 · 73 citations
13. Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization ↗arXiv (Cornell University) · no summary yetJohn J. Miller et al.2021 · 59 citations
14. Understanding and Mitigating the Tradeoff Between Robustness and Accuracy ↗arXiv (Cornell University) · no summary yetAditi Raghunathan et al.2020 · 58 citations
15. Understanding Catastrophic Forgetting in Language Models via Implicit InferencearXiv:2309.10105Suhas Kotha, Jacob Mitchell Springer, Aditi Raghunathan2023 · 45 citations
16. Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming ↗arXiv:2010.11645 · no summary yetSumanth Dathathri et al.2020 · 21 citations
17. Dissecting Adversarial Robustness of Multimodal LM Agents ↗arXiv (Cornell University) · no summary yetChen Henry Wu et al.2024 · 20 citations
18. Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices ↗arXiv (Cornell University) · no summary yetEvan Zheran Liu et al.2020 · 14 citations
19. Maximum Weighted Loss Discrepancy ↗arXiv (Cornell University) · no summary yetFereshte Khani, Aditi Raghunathan, Percy Liang2019 · 11 citations
20. Weight Ensembling Improves Reasoning in Language Models ↗arXiv:2504.10478 · COLM 2025 · no summary yetXingyu Dang et al.2025 · 10 citations
21. Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift ↗arXiv (Cornell University) · no summary yetAnanya Kumar et al.2022 · 10 citations
22. Estimation from Indirect Supervision with Linear Moments ↗arXiv (Cornell University) · no summary yetAditi Raghunathan et al.2016 · 9 citations
23. Overtrained Language Models Are Harder to Fine-Tune ↗arXiv (Cornell University) · no summary yetJacob M. Springer et al.2025 · 8 citations
24. Not-Just-Scaling Laws: Towards a Better Understanding of the Downstream Impact of Language Model Design Decisions ↗Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing · no summary yetEmmy Liu et al.2025 · 6 citations
25. Using Language to Extend to Unseen Domains ↗arXiv (Cornell University) · no summary yetLisa Dunlap et al.2022 · 6 citations
26. Multitask Learning Can Improve Worst-Group Outcomes ↗arXiv (Cornell University) · no summary yetAtharva Kulkarni et al.2023 · 1 citation
27. When Covariate-shifted Data Augmentation Increases Test Error And How to Fix It ↗no summary yetSang Michael Xie et al.2019 · 1 citation
28. Overparameterization hurts worst-group accuracy with spurious correlations ↗International Conference on Machine Learning · no summary yetShiori Sagawa et al.2020
29. Task-Agnostic Robust Encodings for Combating Adversarial Typos ↗no summary yetErik Jones et al.2019

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/aditi-raghunathan/works/