Katherine Lee
Artificial Intelligence · 2018–2023
A researcher in the Science corpus: 14 papers; trusts 752 researchers and is trusted by 2,117 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 760 citations into it; #800 of 36,961 by trust here, #196 by citations
- Natural Language Processing — 331 citations into it; #322 of 5,725 by trust here, #78 by citations
- Computer Vision and Pattern Recognition — 227 citations into it; #1,580 of 21,973 by trust here, #195 by citations
- Safety, Robustness & Interpretability — 191 citations into it; #1,280 of 2,259 by trust here, #210 by citations
- Large Language Models — 156 citations into it; #47 of 810 by trust here, #38 by citations
- Evaluation & Benchmarks — 144 citations into it
- Information Systems — 64 citations into it
- Model Architectures — 56 citations into it
Whom Katherine Lee trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Ilya Sutskever
- Geoffrey E. Hinton
- Yoshua Bengio
- Alex Krizhevsky
- Alex Graves
- Noam Shazeer
- Kaiming He
- Yann LeCun
- Jimmy Ba
Who trusts Katherine Lee overall
- Yi Tay
- Nicholas Carlini
- Daphne Ippolito
- Timo Schick
- Mohit Bansal
- Stella Biderman
- Ana Marasovic
- Nikhil Kandpal
- Eric Wallace
- Sebastian Gehrmann
Papers from Katherine Lee's perspective
Ordered by how strongly the researchers Katherine Lee trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
Their papers
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer (2019) — 26,606 citations
- PaLM: Scaling Language Modeling with Pathways (2022) — 8,214 citations
- Extracting Training Data from Large Language Models (2020) — 3,168 citations
- PaLM 2 Technical Report (2023) — 1,524 citations
- Deduplicating Training Data Makes Language Models Better (2021) — 926 citations
- Quantifying Memorization Across Neural Language Models (2022) — 944 citations
- WT5?! Training Text-to-Text Models to Explain their Predictions (2020) — 219 citations
- Hallucinations in Neural Machine Translation (2018) — 183 citations
- Counterfactual Memorization in Neural Language Models (2021) — 203 citations
- What Does it Mean for a Language Model to Preserve Privacy? (2022) — 331 citations
- Scalable Extraction of Training Data from (Production) Language Models (2023) — 592 citations
- Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy (2022) — 147 citations
- Are aligned neural networks adversarially aligned? (2023) — 387 citations
- Measuring Forgetting of Memorized Training Examples (2022) — 150 citations