Marie-Therese Png

Safety, Robustness & Interpretability · 2020–2023

A researcher in the Science corpus: 2 papers; trusts 13 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Safety, Robustness & Interpretability — 103 citations into it
• Artificial Intelligence — 96 citations into it
• Safety Research — 49 citations into it
• AI Ethics, Fairness & Society — 46 citations into it
• Social Sciences & Humanities — 44 citations into it
• Sociology and Political Science — 43 citations into it
• Information Systems — 20 citations into it
• Human-Computer Interaction — 16 citations into it

Whom Marie-Therese Png trusts overall

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

1. Philip E. Agre
2. Kentaro Toyama
3. John R. Clark
4. D. Harvey
5. Meg Young
6. Vidushi Marda
7. Irene Y. Chen
8. Timnit Gebru
9. Rhema Vaithianathan
10. Lilly C. Irani

Who trusts Marie-Therese Png overall

1. Irene Solaiman

Papers from Marie-Therese Png's perspective

Ordered by how strongly the researchers Marie-Therese Png trusts endorse each paper. Same corpus, a different order for every researcher.

1. Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification
2. Language Models are Few-Shot Learners (Neural Information Processing Systems)
3. Datasheets for datasets
4. Model Cards for Model Reporting
5. Fairness through awareness
6. Race After Technology: Abolitionist Tools for the New Jim Code
7. Big Data's Disparate Impact
8. Energy and Policy Considerations for Deep Learning in NLP
9. To predict and serve?
10. Semantics derived automatically from language corpora contain human-like biases

Their papers

• Evaluating the Social Impact of Generative AI Systems in Systems and Society (2023) — 177 citations
• Decolonial AI: Decolonial Theory as Sociotechnical Foresight in Artificial Intelligence (2020) — 669 citations