Sotabase

Career

· Research Scientist, Anthropic2022–
· Research Advisor, New York University2022–
· Assistant Lecturer, African Institute of Mathematical Sciences2021–2021
· Research Scientist Intern, DeepMind2021–2021
· NLP Research Intern, Facebook AI2019–2020
· NLP Research Intern, Facebook AI2018–2020
· PhD Student, New York University2018–2022
· Deep Learning Research Intern, Université de Montréal2017–2017
· Deep Learning Research Intern, Rice University2016–2017
· Intern And KPCB Fellow, Uber2016–2016
· Software Development Intern, Google2015–2015

Publications (88)

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Neural Information Processing Systems · 2020
11,053
cited
FiLM: Visual Reasoning with a General Conditioning Layer
AAAI Conference on Artificial Intelligence · 2017
2,996
cited
Language Models (Mostly) Know What They Know
arXiv.org · 2022
1,204
cited
Red Teaming Language Models with Language Models
Conference on Empirical Methods in Natural Language Processing · 2022
895
cited
Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting
Neural Information Processing Systems · 2023
779
cited
ELI5: Long Form Question Answering
Annual Meeting of the Association for Computational Linguistics · 2019
746
cited
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
arXiv.org · 2022
656
cited
Discovering Language Model Behaviors with Model-Written Evaluations
Annual Meeting of the Association for Computational Linguistics · 2022
621
cited
Towards Understanding Sycophancy in Language Models
International Conference on Learning Representations · 2023
512
cited
True Few-Shot Learning with Language Models
Neural Information Processing Systems · 2021
492
cited
Measuring Faithfulness in Chain-of-Thought Reasoning
arXiv.org · 2023
321
cited
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
arXiv.org · 2024
285
cited
Pretraining Language Models with Human Preferences
International Conference on Machine Learning · 2023
279
cited
Studying Large Language Model Generalization with Influence Functions
arXiv.org · 2023
276
cited
Many-shot Jailbreaking
Neural Information Processing Systems · 2024
214
cited
Feature-wise transformations
Distill · 2018
210
cited
Debating with More Persuasive LLMs Leads to More Truthful Answers
International Conference on Machine Learning · 2024
208
cited
Unsupervised Question Decomposition for Question Answering
Conference on Empirical Methods in Natural Language Processing · 2020
199
cited
Reasoning Models Don't Always Say What They Think
arXiv.org · 2025
195
cited
The Capacity for Moral Self-Correction in Large Language Models
arXiv.org · 2023
195
cited
Sotabase