Pang Wei Koh

Christopher A. Choquette-Choo

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Merge to Learn: Efficiently Adding Skills to Language Models with Model Merging.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation.

[BibT_eX]

[DOI]

Tong Chen

Akari Asai

Niloofar Mireshghallah

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

2023

Use large language models to promote equity.

[BibT_eX]

[DOI]

CoRR, 2023

OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models.

[BibT_eX]

[DOI]

CoRR, 2023

Are aligned neural networks adversarially aligned?

[BibT_eX]

[DOI]

Nicholas Carlini

Milad Nasr

CoRR, 2023

Proximity-Informed Calibration for Deep Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2023

Leveraging Domain Relations for Domain Generalization.

[BibT_eX]

[DOI]

CoRR, 2023

On the Trade-off of Intra-/Inter-class Diversity for Supervised Pre-training.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

DataComp: In search of the next generation of multimodal datasets.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Are aligned neural networks adversarially aligned?

[BibT_eX]

[DOI]

Nicholas Carlini

Milad Nasr

Christopher A. Choquette-Choo

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Out-of-Domain Robustness via Targeted Augmentations.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation.

[BibT_eX]

[DOI]

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

2022

Stronger data poisoning attacks break data sanitization defenses.

[BibT_eX]

[DOI]

Jacob Steinhardt

Mach. Learn., 2022

Impossibility Theorems for Feature Attribution.

[BibT_eX]

[DOI]

CoRR, 2022

Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Extending the WILDS Benchmark for Unsupervised Adaptation.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Mobility network models of COVID-19 explain inequities and inform reopening.

[BibT_eX]

[DOI]

Nat., 2021

On the Opportunities and Risks of Foundation Models.

[BibT_eX]

[DOI]

CoRR, 2021

Supporting COVID-19 Policy Response with Large-scale Mobility-based Modeling.

[BibT_eX]

[DOI]

Proceedings of the KDD '21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2021

Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Just Train Twice: Improving Group Robustness without Training Group Information.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

WILDS: A Benchmark of in-the-Wild Distribution Shifts.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Selective Classification Can Magnify Disparities Across Groups.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

2020

WILDS: A Benchmark of in-the-Wild Distribution Shifts.

[BibT_eX]

[DOI]

Richard Lanas Phillips

CoRR, 2020

Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims.

[BibT_eX]

[DOI]

Thomas Krendl Gilbert

CoRR, 2020

An Investigation of Why Overparameterization Exacerbates Spurious Correlations.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

Concept Bottleneck Models.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

Distributionally Robust Neural Networks.

[BibT_eX]

[DOI]

Shiori Sagawa

Proceedings of the 8th International Conference on Learning Representations, 2020

ExpBERT: Representation Engineering with Natural Language Explanations.

[BibT_eX]

[DOI]

Shikhar Murty

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020

2019

Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization.

[BibT_eX]

[DOI]

Shiori Sagawa

CoRR, 2019

On the Accuracy of Influence Functions for Measuring Group Effects.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Inferring Multidimensional Rates of Aging from Cross-Sectional Data.

[BibT_eX]

[DOI]

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

Identifying and exploiting influential training examples.

[BibT_eX]

Proceedings of the Symposium Interpretable AI for Well-being: Understanding Cognitive Bias and Social Embeddedness co-located with Association for the Advancement of Artificial Intelligence 2019 Spring Symposium (AAAI-Spring Symposium 2019), 2019

2018

Inferring Multi-Dimensional Rates of Aging from Cross-Sectional Data.

[BibT_eX]

[DOI]

CoRR, 2018

2017

Denoising genome-wide histone ChIP-seq with convolutional neural networks.

[BibT_eX]

[DOI]

Anshul Kundaje

Bioinform., 2017

Certified Defenses for Data Poisoning Attacks.

[BibT_eX]

[DOI]

Jacob Steinhardt

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Understanding Black-box Predictions via Influence Functions.

[BibT_eX]

[DOI]