Aditi Raghunathan

Computer Science · Physical Sciences

22h-index4.7kcitations99works0.62yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

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

Research Topics

Adversarial Robustness in Machine Learning(24), Domain Adaptation and Few-Shot Learning(21), Topic Modeling(12), Advanced Neural Network Applications(11), Machine Learning and Data Classification(11)

Publications99 total

Mode-Conditioning Unlocks Superior Test-Time Scaling
arXiv (Cornell University)·2025Open Access
Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning
ArXiv.org·2025Open Access
ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases
arXiv (Cornell University)·2025Open Access
Understanding the Influence of Synthetic Data for Text Embedders
arXiv (Cornell University)·2025Open Access
Memorization Sinks: Isolating Memorization during LLM Training
arXiv (Cornell University)·2025Open Access
Reasoning as an Adaptive Defense for Safety
arXiv (Cornell University)·2025Open Access
Weight Ensembling Improves Reasoning in Language Models
arXiv (Cornell University)·2025Open Access
Exact Unlearning of Finetuning Data via Model Merging at Scale
arXiv (Cornell University)·2025Open Access
Overtrained Language Models Are Harder to Fine-Tune
ArXiv.org·2025· 1 citedOpen Access
Not-Just-Scaling Laws: Towards a Better Understanding of the Downstream Impact of Language Model Design Decisions
arXiv (Cornell University)·2025Open Access
Mitigating Bias in RAG: Controlling the Embedder
arXiv (Cornell University)·2025Open Access
On the Feasibility of In-Context Probing for Data Attribution
2025Open Access
Understanding the Influence of Synthetic Data for Text Embedders
2025Open Access
Mitigating Bias in RAG: Controlling the Embedder
2025· 2 citedOpen Access
Not-Just-Scaling Laws: Towards a Better Understanding of the Downstream Impact of Language Model Design Decisions
2025Open Access
Scaling Laws for Precision
arXiv (Cornell University)·2024Open Access
Context-Parametric Inversion: Why Instruction Finetuning Can Worsen Context Reliance
arXiv (Cornell University)·2024Open Access
Understanding Finetuning for Factual Knowledge Extraction
arXiv (Cornell University)·2024· 1 citedOpen Access
Dissecting Adversarial Robustness of Multimodal LM Agents
arXiv (Cornell University)·2024· 1 citedOpen Access
Scaling Laws for Data Filtering—Data Curation Cannot be Compute Agnostic
2024· 9 cited
page 1 of 5Next →

Frequent Co-authors

Percy Liang(27), Pang Wei Koh(7), Shiori Sagawa(7), Jacob Steinhardt(7), Sachin Goyal(6), Chelsea Finn(5), Ananya Kumar(5), John C. Duchi(5), Prateek Jain(5), Tengyu Ma(4), Robin Jia(4), Sang Michael Xie(4), J. Zico Kolter(4), Rohan Taori(3), Fanny Yang(3), Yair Carmon(3), Ludwig Schmidt(3), Evan Zheran Liu(3), Zachary C. Lipton(3), Annie Chen(2)