Naomi Saphra

Publication Activity (10 Years)

Years Active: 2013-2024
Publications (10 Years): 42

Top Topics

Phase Transition

Citation Networks

Top Venues

Publications

Naomi Saphra, Eve Fleisig, Kyunghyun Cho, Adam Lopez
First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models. NAACL-HLT (2024)
Tom Sherborne, Naomi Saphra, Pradeep Dasigi, Hao Peng
TRAM: Bridging Trust Regions and Sharpness Aware Minimization. ICLR (2024)
Angelica Chen, Ravid Shwartz-Ziv, Kyunghyun Cho, Matthew L. Leavitt, Naomi Saphra
Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs. ICLR (2024)
Michael Saxon, Ari Holtzman, Peter West, William Yang Wang, Naomi Saphra
Benchmarks as Microscopes: A Call for Model Metrology. CoRR (2024)
Zachary Ankner, Naomi Saphra, Davis W. Blalock, Jonathan Frankle, Matthew L. Leavitt
Dynamic Masking Rate Schedules for MLM Pretraining. EACL (2) (2024)
Edwin Zhang, Vincent Zhu, Naomi Saphra, Anat Kleiman, Benjamin L. Edelman, Milind Tambe, Sham M. Kakade, Eran Malach
Transcendence: Generative Models Can Outperform The Experts That Train Them. CoRR (2024)
Divyansh Singhvi, Andrej Erkelens, Raghav Jain, Diganta Misra, Naomi Saphra
Knowing Your Nonlinearities: Shapley Interactions Reveal the Underlying Structure of Data. CoRR (2024)
USVSN Sai Prashanth, Alvin Deng, Kyle O'Brien, Jyothir S. V, Mohammad Aflah Khan, Jaydeep Borkar, Christopher A. Choquette-Choo, Jacob Ray Fuehne, Stella Biderman, Tracy Ke, Katherine Lee, Naomi Saphra
Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon. CoRR (2024)
Victoria R. Li, Yida Chen, Naomi Saphra
ChatGPT Doesn't Trust Chargers Fans: Guardrail Sensitivity in Context. CoRR (2024)
Michael Y. Hu, Angelica Chen, Naomi Saphra, Kyunghyun Cho
Latent State Models of Training Dynamics. CoRR (2023)
Tom Sherborne, Naomi Saphra, Pradeep Dasigi, Hao Peng
TRAM: Bridging Trust Regions and Sharpness Aware Minimization. CoRR (2023)
Naomi Saphra, Eve Fleisig, Kyunghyun Cho, Adam Lopez
First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models. CoRR (2023)
Ian Berlot-Attwell, A. Michael Carrell, Kumar Krishna Agrawal, Yash Sharma, Naomi Saphra
Attribute Diversity Determines the Systematicity Gap in VQA. CoRR (2023)
Dieuwke Hupkes, Mario Giulianelli, Verna Dankers, Mikel Artetxe, Yanai Elazar, Tiago Pimentel, Christos E. Christodoulopoulos, Karim Lasri, Naomi Saphra, Arabella Sinclair, Dennis Ulmer, Florian Schottmann, Khuyagbaatar Batsuren, Kaiser Sun, Koustuv Sinha, Leila Khalatbari, Maria Ryskina, Rita Frieske, Ryan Cotterell, Zhijing Jin
A taxonomy and review of generalization research in NLP. Nat. Mac. Intell. 5 (10) (2023)
Jeevesh Juneja, Rachit Bansal, Kyunghyun Cho, João Sedoc, Naomi Saphra
Linear Connectivity Reveals Generalization Strategies. ICLR (2023)
Michael Y. Hu, Angelica Chen, Naomi Saphra, Kyunghyun Cho
Latent State Models of Training Dynamics. Trans. Mach. Learn. Res. 2023 (2023)
Angelica Chen, Ravid Schwartz-Ziv, Kyunghyun Cho, Matthew L. Leavitt, Naomi Saphra
Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs. CoRR (2023)
Yash Gondhalekar, Sultan Hassan, Naomi Saphra, Sambatra Andrianomena
Towards out-of-distribution generalization in large-scale astronomical surveys: robust networks learn similar representations. CoRR (2023)
Zachary Ankner, Naomi Saphra, Davis W. Blalock, Jonathan Frankle, Matthew L. Leavitt
Dynamic Masking Rate Schedules for MLM Pretraining. CoRR (2023)
Dieuwke Hupkes, Mario Giulianelli, Verna Dankers, Mikel Artetxe, Yanai Elazar, Tiago Pimentel, Christos Christodoulopoulos, Karim Lasri, Naomi Saphra, Arabella Sinclair, Dennis Ulmer, Florian Schottmann, Khuyagbaatar Batsuren, Kaiser Sun, Koustuv Sinha, Leila Khalatbari, Maria Ryskina, Rita Frieske, Ryan Cotterell, Zhijing Jin
State-of-the-art generalisation research in NLP: a taxonomy and review. CoRR (2022)
Josef Valvoda, Naomi Saphra, Jonathan Rawski, Ryan Cotterell, Adina Williams
Learning Transductions to Test Systematic Compositionality. CoRR (2022)
Jeevesh Juneja, Rachit Bansal, Kyunghyun Cho, João Sedoc, Naomi Saphra
Linear Connectivity Reveals Generalization Strategies. CoRR (2022)
Josef Valvoda, Naomi Saphra, Jonathan Rawski, Adina Williams, Ryan Cotterell
Benchmarking Compositionality with Formal Languages. COLING (2022)
Bingchen Zhao, Yuling Gu, Jessica Zosa Forde, Naomi Saphra
One Venue, Two Conferences: The Separation of Chinese and American Citation Networks. CoRR (2022)
Thibault Sellam, Steve Yadlowsky, Ian Tenney, Jason Wei, Naomi Saphra, Alexander D'Amour, Tal Linzen, Jasmijn Bastings, Iulia Raluca Turc, Jacob Eisenstein, Dipanjan Das, Ellie Pavlick
The MultiBERTs: BERT Reproductions for Robustness Analysis. ICLR (2022)
Jennifer C. White, Tiago Pimentel, Naomi Saphra, Ryan Cotterell
A Non-Linear Structural Probe. NAACL-HLT (2021)
Jennifer C. White, Tiago Pimentel, Naomi Saphra, Ryan Cotterell
A Non-Linear Structural Probe. CoRR (2021)
Thibault Sellam, Steve Yadlowsky, Jason Wei, Naomi Saphra, Alexander D'Amour, Tal Linzen, Jasmijn Bastings, Iulia Turc, Jacob Eisenstein, Dipanjan Das, Ian Tenney, Ellie Pavlick
The MultiBERTs: BERT Reproductions for Robustness Analysis. CoRR (2021)
Tiago Pimentel, Naomi Saphra, Adina Williams, Ryan Cotterell
Pareto Probing: Trading Off Accuracy for Complexity. EMNLP (1) (2020)
Tiago Pimentel, Naomi Saphra, Adina Williams, Ryan Cotterell
Pareto Probing: Trading Off Accuracy for Complexity. CoRR (2020)
Mohammad Tahaei, Kami Vaniea, Naomi Saphra
Understanding Privacy-Related Questions on Stack Overflow. CHI (2020)
Naomi Saphra, Adam Lopez
LSTMs Compose (and Learn) Bottom-Up. CoRR (2020)
Naomi Saphra, Adam Lopez
Word Interdependence Exposes How LSTMs Compose Representations. CoRR (2020)
Naomi Saphra, Adam Lopez
LSTMS Compose - and Learn - Bottom-Up. EMNLP (Findings) (2020)
Naomi Saphra, Adam Lopez
Understanding Learning Dynamics Of Language Models with SVCCA. NAACL-HLT (1) (2019)
Naomi Saphra, Adam Lopez
Sparsity Emerges Naturally in Neural Language Models. CoRR (2019)
Yekun Chai, Naomi Saphra, Adam Lopez
How to Evaluate Word Representations of Informal Domain? CoRR (2019)
Naomi Saphra, Adam Lopez
Language Models Learn POS First. BlackboxNLP@EMNLP (2018)
Naomi Saphra, Adam Lopez
Understanding Learning Dynamics Of Language Models with SVCCA. CoRR (2018)
Graham Neubig, Chris Dyer, Yoav Goldberg, Austin Matthews, Waleed Ammar, Antonios Anastasopoulos, Miguel Ballesteros, David Chiang, Daniel Clothiaux, Trevor Cohn, Kevin Duh, Manaal Faruqui, Cynthia Gan, Dan Garrette, Yangfeng Ji, Lingpeng Kong, Adhiguna Kuncoro, Gaurav Kumar, Chaitanya Malaviya, Paul Michel, Yusuke Oda, Matthew Richardson, Naomi Saphra, Swabha Swayamdipta, Pengcheng Yin
DyNet: The Dynamic Neural Network Toolkit. CoRR (2017)
Naomi Saphra
Evaluating Informal-Domain Word Representations With UrbanDictionary. RepEval@ACL (2016)
Naomi Saphra, Adam Lopez
Evaluating Informal-Domain Word Representations With UrbanDictionary. CoRR (2016)
Naomi Saphra, Adam Lopez
AMRICA: an AMR Inspector for Cross-language Alignments. HLT-NAACL (2015)
Andrea Vedaldi, Siddharth Mahendran, Stavros Tsogkas, Subhransu Maji, Ross B. Girshick, Juho Kannala, Esa Rahtu, Iasonas Kokkinos, Matthew B. Blaschko, David J. Weiss, Ben Taskar, Karen Simonyan, Naomi Saphra, Sammy Mohamed
Understanding Objects in Detail with Fine-Grained Attributes. CVPR (2014)
Nathan Schneider, Brendan O'Connor, Naomi Saphra, David Bamman, Manaal Faruqui, Noah A. Smith, Chris Dyer, Jason Baldridge
A Framework for (Under)specifying Dependency Syntax without Overloading Annotators. LAW@ACL (2013)
Nathan Schneider, Brendan O'Connor, Naomi Saphra, David Bamman, Manaal Faruqui, Noah A. Smith, Chris Dyer, Jason Baldridge
A framework for (under)specifying dependency syntax without overloading annotators. CoRR (2013)