Myra Cheng

Artificial Intelligence · 2021–2023

A researcher in the Science corpus: 4 papers; trusts 30 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 222 citations into it
• Natural Language Processing — 146 citations into it
• Safety, Robustness & Interpretability — 139 citations into it
• Sociology and Political Science — 77 citations into it
• Large Language Models — 60 citations into it
• Safety Research — 50 citations into it
• Information Systems — 32 citations into it
• Gender Studies — 17 citations into it

Whom Myra Cheng trusts overall

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

1. N. Ellemers
2. Aylin Caliskan
3. Li Lucy
4. Clayton J. Hutto
5. Nikita Nangia
6. Moin Nadeem
7. Timo Schick
8. Burt L. Monroe
9. David Bamman
10. Soumya Barikeri

Papers from Myra Cheng's perspective

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

1. Attention is All you Need (Neural Information Processing Systems)
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
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. Language Models are Unsupervised Multitask Learners
9. Gradient-based learning applied to document recognition
10. GloVe: Global Vectors for Word Representation

Their papers

• Ethical and social risks of harm from Language Models (2021) — 1,580 citations
• Taxonomy of Risks posed by Language Models (2022) — 1,066 citations
• Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale (2022) — 535 citations
• Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models (2023) — 323 citations