Maarten Sap
Artificial Intelligence · 2014–2025
A researcher in the Science corpus: 33 papers; trusts 1,241 researchers and is trusted by 401 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 755 citations into it; #1,653 of 36,961 by trust here, #806 by citations
- Natural Language Processing — 480 citations into it; #575 of 5,725 by trust here, #330 by citations
- Safety, Robustness & Interpretability — 175 citations into it; #165 of 2,259 by trust here, #87 by citations
- Computer Vision and Pattern Recognition — 136 citations into it; #21,922 of 21,973 by trust here, #10,297 by citations
- Evaluation & Benchmarks — 119 citations into it
- Large Language Models — 110 citations into it; #284 of 810 by trust here, #184 by citations
- Sociology and Political Science — 109 citations into it; #3,798 of 22,891 by trust here, #692 by citations
- Social Psychology — 107 citations into it; #8,544 of 15,767 by trust here, #3,494 by citations
Whom Maarten Sap trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Diederik P. Kingma
- Alec Radford
- Yoshua Bengio
- Ilya Sutskever
- Alex Krizhevsky
- Yann LeCun
- Richard Socher
- Kaiming He
- Sepp Hochreiter
Who trusts Maarten Sap overall
- Yulia Tsvetkov
- Yejin Choi
- Caleb Ziems
- Anjalie Field
- Emily Dinan
- Emily Sheng
- Zeerak Talat
- Sachin Kumar
- Fatemehsadat Mireshghallah
- Ximing Lu
Papers from Maarten Sap's perspective
Ordered by how strongly the researchers Maarten Sap trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- 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
- RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models (2020) — 1,775 citations
- Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2022) — 2,561 citations
- The Risk of Racial Bias in Hate Speech Detection (2019) — 1,043 citations
- Social Bias Frames: Reasoning about Social and Power Implications of Language (2019) — 640 citations
- COMET: Commonsense Transformers for Automatic Knowledge Graph Construction (2019) — 1,043 citations
- Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection (2021) — 408 citations
- DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts (2021) — 533 citations
- Detoxifying Language Models Risks Marginalizing Minority Voices (2021) — 148 citations
- The Effect of Different Writing Tasks on Linguistic Style: A Case Study of the ROC Story Cloze Task (2017) — 121 citations
- ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection (2022) — 626 citations
- Documenting the English Colossal Clean Crawled Corpus (2021) — 51 citations
- Event2Mind: Commonsense Inference on Events, Intents, and Reactions (2018) — 207 citations
- Story Cloze Task: UW NLP System (2017) — 48 citations
- Challenges in Automated Debiasing for Toxic Language Detection (2021) — 162 citations
- Delphi: Towards Machine Ethics and Norms (2021) — 135 citations
- Modeling Naive Psychology of Characters in Simple Commonsense Stories (2018) — 113 citations
- Social Chemistry 101: Learning to Reason about Social and Moral Norms (2020) — 352 citations
- Sounding Board: A User-Centric and Content-Driven Social Chatbot (2018) — 61 citations
- Connotation Frames of Power and Agency in Modern Films (2017) — 122 citations
- PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction (2020) — 82 citations