Daphne Ippolito

Artificial Intelligence · 2019–2024

A researcher in the Science corpus: 23 papers; trusts 331 researchers and is trusted by 31 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 578 citations into it; #7,867 of 35,345 by trust here, #797 by citations
• Natural Language Processing — 304 citations into it; #2,523 of 5,688 by trust here, #1,221 by citations
• Computer Vision and Pattern Recognition — 196 citations into it
• Safety, Robustness & Interpretability — 161 citations into it
• Large Language Models — 141 citations into it; #726 of 799 by trust here, #95 by citations
• Evaluation & Benchmarks — 114 citations into it; #2,282 of 3,147 by trust here, #517 by citations
• Information Systems — 59 citations into it
• Generative Models — 52 citations into it

Whom Daphne Ippolito trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Geoffrey E. Hinton
2. Diederik P. Kingma
3. Yoshua Bengio
4. Ilya Sutskever
5. Alex Krizhevsky
6. Alec Radford
7. Yann LeCun
8. Kaiming He
9. Ashish Vaswani
10. Kyunghyun Cho

Who trusts Daphne Ippolito overall

1. Hugh Zhang
2. Jooyoung Lee
3. Stella Biderman
4. Nicholas Carlini
5. Sebastian Gehrmann
6. Marc Marone
7. Hugh Zhang
8. Thai Le
9. Kalpesh Krishna
10. Hayden S. Helm

Papers from Daphne Ippolito's perspective

Ordered by how strongly the researchers Daphne Ippolito trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Attention is All you Need (Neural Information Processing Systems)
4. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
5. Long Short-Term Memory
6. ImageNet: A large-scale hierarchical image database
7. Gradient-based learning applied to document recognition
8. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
9. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
10. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)

Their papers

• PaLM: Scaling Language Modeling with Pathways (2022) — 8,214 citations
• Deduplicating Training Data Makes Language Models Better (2021) — 926 citations
• Quantifying Memorization Across Neural Language Models (2022) — 944 citations
• Extracting Training Data from Diffusion Models (2023) — 986 citations
• SynthBio: A Case Study in Human-AI Collaborative Curation of Text Datasets (2021) — 25 citations
• Trading Off Diversity and Quality in Natural Language Generation (2020) — 133 citations
• Automatic Detection of Generated Text is Easiest when Humans are Fooled (2019) — 524 citations
• Scalable Extraction of Training Data from (Production) Language Models (2023) — 592 citations
• Comparison of Diverse Decoding Methods from Conditional Language Models (2019) — 135 citations
• Counterfactual Memorization in Neural Language Models (2021) — 203 citations
• A Recipe for Arbitrary Text Style Transfer with Large Language Models (2021) — 158 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
• RoFT: A Tool for Evaluating Human Detection of Machine-Generated Text (2020) — 71 citations
• Contact Tracing Mobile Apps for COVID-19: Privacy Considerations and Related Trade-offs (2020) — 462 citations
• Measuring Forgetting of Memorized Training Examples (2022) — 150 citations
• Gemma: Open Models Based on Gemini Research and Technology (2024) — 1,150 citations
• Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2022) — 2,561 citations
• Wordcraft: Story Writing With Large Language Models (2022) — 460 citations
• SynthBio: A Case Study in Faster Curation of Text Datasets (2021) — 16 citations