--- title: "Naomi Saphra · Boston University — author profile and papers" description: "Naomi Saphra, Boston University: 2 papers on Elamur Research (2019–2024), h-index 10 — affiliations, topics, co-authors and who cites…" canonical: "https://research.elamur.ai/free/en/authors/naomi-saphra/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/naomi-saphra/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Naomi Saphra # Naomi Saphra Naomi Saphra has 2 papers in our library, in 2019–2024, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/); often with [Adam Lopez](https://md.research.elamur.ai/free/en/authors/adam-lopez/), [Benjamin L. Edelman](https://md.research.elamur.ai/free/en/authors/benjamin-l-edelman/), [Eran Malach](https://md.research.elamur.ai/free/en/authors/eran-malach/). 2 papers in our library · 2019–2024 [OpenAlex](https://openalex.org/A5010251681) · [ORCID](https://orcid.org/0000-0001-8607-3515) · [**h-index 10**](https://openalex.org/authors/A5010251681) · [45 works](https://openalex.org/works?filter=author.id:A5010251681) · [724 citations](https://openalex.org/works?filter=author.id:A5010251681&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/naomi-saphra/#papers) · [🔗 Cited 470 times in our library](https://md.research.elamur.ai/free/en/authors/naomi-saphra/cited-by/) · [9 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #7988](https://md.research.elamur.ai/free/en/paper-stars/page/80/#star-7988) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Naomi+Saphra) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Naomi+Saphra) · [dblp](https://dblp.org/search?q=Naomi+Saphra) · [ACL Anthology](https://aclanthology.org/search/?q=Naomi+Saphra) ## Affiliations [🎓**Boston University** Boston · United States 2025–2026 · 2 papersEmployment since 2026 · Assistant Professor, Faculty of Computing and Data Science*current*](https://md.research.elamur.ai/free/en/universities/boston-university/) · [🎓**Harvard University** Cambridge · United States 2022–2026 · 13 papersEmployment 2023–2026 · Kempner Research Fellow, Kempner Institute for the Study of Natural and Artificial Intelligence](https://md.research.elamur.ai/free/en/universities/harvard-university/) · [🎓**University of Edinburgh** Edinburgh · United Kingdom 2016–2021 · 10 papersEducation until 2021 · PhD, informatics](https://md.research.elamur.ai/free/en/universities/university-of-edinburgh/) · [🎓**Johns Hopkins University** Baltimore · United States 2013–2015 · 3 papersEducation until 2015 · MEng, computer science](https://md.research.elamur.ai/free/en/universities/johns-hopkins-university/) · [🎓**New York University** New York · United States 2021–2023 · 2 papersEmployment 2021–2023 · Postdoctoral Researcher, Center for Data Science](https://md.research.elamur.ai/free/en/universities/new-york-university/) · [🎓**University of Cambridge** Cambridge · United Kingdom 2020–2021 · 2 papers](https://md.research.elamur.ai/free/en/universities/university-of-cambridge/) · [🎓**Carnegie Mellon University** Pittsburgh · United States 2012–2013 · 2 papersEducation until 2013 · BS, computer science](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) · [🏢**Google** Mountain View · United States 2019–2021 · 1 paperEmployment 2019–2020 · Research intern](https://md.research.elamur.ai/free/en/companies/google/) 🏛️**MosaicML** New York · [United States](https://md.research.elamur.ai/free/en/countries/united-states/) 2021–2023Employment 2021–2023 · Consultant From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. ## Fields, topics and concepts Of its works in our library, with the number of works on each. 📚 Shelves 5 The field of science this work belongs to (OpenAlex fields).[Arts and Humanities · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Computer Science · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Language and Linguistics · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Computer Vision and Pattern Recognition · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) 🧭 Topics 1 Research subjects and languages the work is about.[Language models & pretraining · 1 work](https://md.research.elamur.ai/free/en/topics/language-models/) ## Works by year ### 2020s [**2024** 1 paper](https://md.research.elamur.ai/free/en/authors/naomi-saphra/year/2024/) ### 2010s [**2019** 1 paper](https://md.research.elamur.ai/free/en/authors/naomi-saphra/year/2019/) ## Papers The most cited first (OpenAlex and our library). 1. **[Understanding Learning Dynamics Of Language Models with SVCCA](https://md.research.elamur.ai/free/en/papers/saphra-2019-understanding-learning-dynamics-language-models/)** *(2019 · 107 citations)* Earlier work showed that neural networks implicitly capture linguistic categories, but not how those encodings develop during training. 2. **[Transcendence: Generative Models Can Outperform The Experts That Train Them](https://md.research.elamur.ai/free/en/papers/zhang-2024-transcendence-generative-models-outperform-experts/)** *(2024 · 12 citations)* Models trained with cross-entropy learn to mimic the distribution of their training data. This suggests they cannot outperform the humans who produced that data. The authors examine this assumption and define "transcendence" as a generative model earning higher reward than every expert behind its training set. ## All works 11 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them. 1. **[State-of-the-art generalisation research in NLP: A taxonomy and review ↗](https://doi.org/10.1038/s42256-023-00729-y) arXiv:2210.03050 · Nat Mach Intell 5, 1161-1174 (2023) · no summary yet**Dieuwke Hupkes et al.*2022 · 120 citations* 2. **[Understanding Learning Dynamics Of Language Models with SVCCA](https://md.research.elamur.ai/free/en/papers/saphra-2019-understanding-learning-dynamics-language-models/) [Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)](https://md.research.elamur.ai/free/en/venues/naacl/)**Naomi Saphra, Adam Lopez*2019 · 107 citations* 3. **[Understanding Objects in Detail with Fine-Grained Attributes ↗](https://doi.org/10.1109/cvpr.2014.463) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Andrea Vedaldi et al.*2014 · 92 citations* 4. **[The MultiBERTs: BERT Reproductions for Robustness Analysis ↗](https://arxiv.org/abs/2106.16163) arXiv:2106.16163 · no summary yet**Thibault Sellam et al.*2021 · 57 citations* 5. **[Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs ↗](https://arxiv.org/abs/2309.07311) arXiv (Cornell University) · no summary yet**Angelica Chen et al.*2023 · 49 citations* 6. **[Linear Connectivity Reveals Generalization Strategies ↗](https://arxiv.org/abs/2205.12411) arXiv (Cornell University) · no summary yet**Jeevesh Juneja et al.*2022 · 32 citations* 7. **[First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models ↗](https://aclanthology.org/2024.naacl-long.128/) Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) · no summary yet**Naomi Saphra et al.*2024 · 18 citations* 8. **[AMRICA: an AMR Inspector for Cross-language Alignments ↗](https://aclanthology.org/N15-3008/) Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations · no summary yet**Naomi Saphra, Adam Lopez*2015 · 16 citations* 9. **[Transcendence: Generative Models Can Outperform The Experts That Train Them](https://md.research.elamur.ai/free/en/papers/zhang-2024-transcendence-generative-models-outperform-experts/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Edwin Zhang, Vincent Zhu, Naomi Saphra, et al.*2024 · 12 citations* 10. **[Latent State Models of Training Dynamics ↗](https://arxiv.org/abs/2308.09543) arXiv (Cornell University) · no summary yet**Michael Y. Hu et al.*2023 · 7 citations* 11. **[Towards a detailed understanding of objects and scenes in natural images ↗](https://openalex.org/W2524969449) INRIA a CCSD electronic archive server · no summary yet**Matthew B. Blaschko et al.*2012 · 2 citations* ## Co-authors here 4 co-authors with a page, the most papers together first. - [Adam Lopez](https://md.research.elamur.ai/free/en/authors/adam-lopez/) - [Benjamin L. Edelman](https://md.research.elamur.ai/free/en/authors/benjamin-l-edelman/) - [Eran Malach](https://md.research.elamur.ai/free/en/authors/eran-malach/) - [Sham M. Kakade](https://md.research.elamur.ai/free/en/authors/sham-m-kakade/) ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - [Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)](https://md.research.elamur.ai/free/en/venues/naacl/): [NAACL 2019](https://md.research.elamur.ai/free/en/venues/naacl/2019/) - [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/): [NeurIPS 2024](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2024/) - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - INRIA a CCSD electronic archive server - Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations - Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) ## Cited by Papers of our library cite their works 470 times (of the 149,439 papers whose bibliographies we read); [88 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/naomi-saphra/cited-by/). Updated 3 November 2026