Ellie Pavlick
Brown University
H-index: 35
North America-United States
Top articles of Ellie Pavlick
Title | Journal | Author(s) | Publication Date |
|---|---|---|---|
Transformer Mechanisms Mimic Frontostriatal Gating Operations When Trained on Human Working Memory Tasks | arXiv preprint arXiv:2402.08211 | Aaron Traylor Jack Merullo Michael J Frank Ellie Pavlick | 2024/2/13 |
mOthello: When Do Cross-Lingual Representation Alignment and Cross-Lingual Transfer Emerge in Multilingual Models? | arXiv preprint arXiv:2404.12444 | Tianze Hua Tian Yun Ellie Pavlick | 2024/4/18 |
Bayesian preference elicitation with language models | arXiv preprint arXiv:2403.05534 | Kunal Handa Yarin Gal Ellie Pavlick Noah Goodman Jacob Andreas | 2024/3/8 |
Understanding Subjectivity through the Lens of Motivational Context in Model-Generated Image Satisfaction | arXiv preprint arXiv:2403.05576 | Senjuti Dutta Sherol Chen Sunny Mak Amnah Ahmad Katherine Collins | 2024/2/27 |
Human Curriculum Effects Emerge with In-Context Learning in Neural Networks | arXiv preprint arXiv:2402.08674 | Jacob Russin Ellie Pavlick Michael J Frank | 2024/2/13 |
Language models implement simple word2vec-style vector arithmetic | arXiv preprint arXiv:2305.16130 | Jack Merullo Carsten Eickhoff Ellie Pavlick | 2023/5/25 |
Properties of LoTs: The footprints or the bear itself? | Sam McGrath Jacob Russin Ellie Pavlick Roman Feiman | 2023/4 | |
Deep neural networks can learn generalizable same-different visual relations | arXiv preprint arXiv:2310.09612 | Alexa R Tartaglini Sheridan Feucht Michael A Lepori Wai Keen Vong Charles Lovering | 2023/10/14 |
Emergence of abstract state representations in embodied sequence modeling | arXiv preprint arXiv:2311.02171 | Tian Yun Zilai Zeng Kunal Handa Ashish V Thapliyal Bo Pang | 2023/11/3 |
Testing Causal Models of Word Meaning in GPT-3 and-4 | arXiv preprint arXiv:2305.14630 | Sam Musker Ellie Pavlick | 2023/5/24 |
Simfluence: Modeling the influence of individual training examples by simulating training runs | arXiv preprint arXiv:2303.08114 | Kelvin Guu Albert Webson Ellie Pavlick Lucas Dixon Ian Tenney | 2023/3/14 |
Circuit component reuse across tasks in transformer language models | arXiv preprint arXiv:2310.08744 | Jack Merullo Carsten Eickhoff Ellie Pavlick | 2023/10/12 |
Uncovering Intermediate Variables in Transformers using Circuit Probing | arXiv e-prints | Michael A Lepori Thomas Serre Ellie Pavlick | 2023/11 |
Break it down: Evidence for structural compositionality in neural networks | Advances in Neural Information Processing Systems | Michael Lepori Thomas Serre Ellie Pavlick | 2023/12/15 |
Training priors predict text-to-image model performance | arXiv preprint arXiv:2306.01755 | Charles Lovering Ellie Pavlick | 2023/5/23 |
How Can Deep Neural Networks Inform Theory in Psychological Science? | Sam Whitman McGrath Jacob Russin Ellie Pavlick Roman Feiman | 2023/11 | |
NeuroSurgeon: A toolkit for subnetwork analysis | arXiv preprint arXiv:2309.00244 | Michael A Lepori Ellie Pavlick Thomas Serre | 2023/9/1 |
Comparing trajectory and vision modalities for verb representation | arXiv preprint arXiv:2303.12737 | Dylan Ebert Chen Sun Ellie Pavlick | 2023/3/8 |
Bloom: A 176b-parameter open-access multilingual language model | Teven Le Scao Angela Fan Christopher Akiki Ellie Pavlick Suzana Ilić | 2023/11/20 | |
A mechanism for solving relational tasks in transformer language models | Jack Merullo Carsten Eickhoff Ellie Pavlick | 2023/5 |
Co-Authors
