Paul Röttger

Artificial Intelligence · 2020–2023

A researcher in the Science corpus: 4 papers; trusts 63 researchers and is trusted by 3 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 154 citations into it; #27,620 of 35,345 by trust here, #11,921 by citations
• Natural Language Processing — 104 citations into it; #5,163 of 5,688 by trust here, #3,478 by citations
• Safety, Robustness & Interpretability — 71 citations into it
• Evaluation & Benchmarks — 33 citations into it
• Large Language Models — 31 citations into it; #775 of 799 by trust here, #735 by citations
• Computer Vision and Pattern Recognition — 17 citations into it
• Communication — 14 citations into it
• Sociology and Political Science — 13 citations into it

Whom Paul Röttger trusts overall

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

1. Jacob Devlin
2. Emily M. Bender
3. Zeerak Talat
4. Bertie Vidgen
5. Geoffrey E. Hinton
6. Yoshua Bengio
7. Diederik P. Kingma
8. Alex Krizhevsky
9. Ilya Sutskever
10. Rico Sennrich

Who trusts Paul Röttger overall

1. Kelvin Luu
2. Bertie Vidgen
3. Debora Nozza
4. Federico Bianchi
5. Douwe Kiela
6. Nathan Lambert
7. Todor Markov
8. Seungju Han
9. Daniel Khashabi
10. Ethan Perez

Papers from Paul Röttger's perspective

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

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

Their papers

• HateCheck: Functional Tests for Hate Speech Detection Models (2020) — 368 citations
• Temporal Adaptation of BERT and Performance on Downstream Document Classification: Insights from Social Media (2021) — 85 citations
• XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models (2023) — 447 citations
• Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions (2023) — 413 citations