Naomi Saphra

68 papers A* 13B 1Journal 40Unranked 11
YearRankTypeTitle / Venue / Authors
2025 J jnl
A Taxonomy of Transcendence.
CoRR
Natalie Abreu, Edwin Zhang, Eran Malach, Naomi Saphra
2025 J jnl
Can Interpretation Predict Behavior on Unseen Data?
CoRR
Victoria R. Li, Jenny Kaufmann, Martin Wattenberg, David Alvarez-Melis, Naomi Saphra
2025 A* conf
Data Drives Unstable Hierarchical Generalization in LMs.
EMNLP
Tian Qin, Naomi Saphra, David Alvarez-Melis
2025 J jnl
Distributional Scaling Laws for Emergent Capabilities.
CoRR
Rosie Zhao, Tian Qin, David Alvarez-Melis, Sham M. Kakade, Naomi Saphra
2025 J jnl
Do Natural Language Descriptions of Model Activations Convey Privileged Information?
CoRR
Millicent Li, Alberto Mario Ceballos-Arroyo, Giordano Rogers, Naomi Saphra, Byron C. Wallace
2025 J jnl
Hidden Breakthroughs in Language Model Training.
CoRR
Sara Kangaslahti, Elan Rosenfeld, Naomi Saphra
2025 J jnl
Interpreting the Linear Structure of Vision-language Model Embedding Spaces.
CoRR
Isabel Papadimitriou, Huangyuan Su, Thomas Fel, Naomi Saphra, Sham M. Kakade, Stephanie Gil
2025 A* conf
PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs.
ICLR
Oskar van der Wal, Pietro Lesci, Max Müller-Eberstein, Naomi Saphra, Hailey Schoelkopf, Willem H. Zuidema, Stella Biderman
2025 J jnl
PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs.
CoRR
Oskar van der Wal, Pietro Lesci, Max Müller-Eberstein, Naomi Saphra, Hailey Schoelkopf, Willem H. Zuidema, Stella Biderman
2025 A* conf
Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon.
ICLR
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
2025 J jnl
Understanding Electro-communication and Electro-sensing in Weakly Electric Fish using Multi-Agent Deep Reinforcement Learning.
CoRR
Satpreet H. Singh, Sonja Johnson-Yu, Zhouyang Lu, Aaron Walsman, Federico Pedraja, Denis Turcu, Pratyusha Sharma, Naomi Saphra, Nathaniel B. Sawtell, Kanaka Rajan
2025 — conf
Using Shapley interactions to understand how models use structure.
ACL (1)
Divyansh Singhvi, Diganta Misra, Andrej Erkelens, Raghav Jain, Isabel Papadimitriou, Naomi Saphra
2024 A* conf
Attribute Diversity Determines the Systematicity Gap in VQA.
EMNLP
Ian Berlot-Attwell, Kumar Krishna Agrawal, Annabelle Michael Carrell, Yash Sharma, Naomi Saphra
2024 J jnl
Benchmarks as Microscopes: A Call for Model Metrology.
CoRR
Michael Saxon, Ari Holtzman, Peter West, William Yang Wang, Naomi Saphra
2024 A* conf
ChatGPT Doesn't Trust Chargers Fans: Guardrail Sensitivity in Context.
EMNLP
Victoria R. Li, Yida Chen, Naomi Saphra
2024 J jnl
ChatGPT Doesn't Trust Chargers Fans: Guardrail Sensitivity in Context.
CoRR
Victoria R. Li, Yida Chen, Naomi Saphra
2024 — conf
Dynamic Masking Rate Schedules for MLM Pretraining.
EACL (2)
Zachary Ankner, Naomi Saphra, Davis W. Blalock, Jonathan Frankle, Matthew L. Leavitt
2024 A* conf
Fast Forwarding Low-Rank Training.
EMNLP
Adir Rahamim, Naomi Saphra, Sara Kangaslahti, Yonatan Belinkov
2024 J jnl
Fast Forwarding Low-Rank Training.
CoRR
Adir Rahamim, Naomi Saphra, Sara Kangaslahti, Yonatan Belinkov
2024 — conf
First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models.
NAACL-HLT
Naomi Saphra, Eve Fleisig, Kyunghyun Cho, Adam Lopez
2024 J jnl
Knowing Your Nonlinearities: Shapley Interactions Reveal the Underlying Structure of Data.
CoRR
Divyansh Singhvi, Andrej Erkelens, Raghav Jain, Diganta Misra, Naomi Saphra
2024 J jnl
Mechanistic?
CoRR
Naomi Saphra, Sarah Wiegreffe
2024 J jnl
Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon.
CoRR
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
2024 J jnl
Sometimes I am a Tree: Data Drives Unstable Hierarchical Generalization.
CoRR
Tian Qin, Naomi Saphra, David Alvarez-Melis
2024 A* conf
Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs.
ICLR
Angelica Chen, Ravid Shwartz-Ziv, Kyunghyun Cho, Matthew L. Leavitt, Naomi Saphra
2024 A* conf
TRAM: Bridging Trust Regions and Sharpness Aware Minimization.
ICLR
Tom Sherborne, Naomi Saphra, Pradeep Dasigi, Hao Peng
2024 A* conf
Transcendence: Generative Models Can Outperform The Experts That Train Them.
NeurIPS
Edwin Zhang, Vincent Zhu, Naomi Saphra, Anat Kleiman, Benjamin L. Edelman, Milind Tambe, Sham M. Kakade, Eran Malach
2024 J jnl
Transcendence: Generative Models Can Outperform The Experts That Train Them.
CoRR
Edwin Zhang, Vincent Zhu, Naomi Saphra, Anat Kleiman, Benjamin L. Edelman, Milind Tambe, Sham M. Kakade, Eran Malach
2023 J jnl
A taxonomy and review of generalization research in NLP.
Nat. Mac. Intell.
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
2023 J jnl
Attribute Diversity Determines the Systematicity Gap in VQA.
CoRR
Ian Berlot-Attwell, A. Michael Carrell, Kumar Krishna Agrawal, Yash Sharma, Naomi Saphra
2023 J jnl
Dynamic Masking Rate Schedules for MLM Pretraining.
CoRR
Zachary Ankner, Naomi Saphra, Davis W. Blalock, Jonathan Frankle, Matthew L. Leavitt
2023 J jnl
First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models.
CoRR
Naomi Saphra, Eve Fleisig, Kyunghyun Cho, Adam Lopez
2023 J jnl
Latent State Models of Training Dynamics.
CoRR
Michael Y. Hu, Angelica Chen, Naomi Saphra, Kyunghyun Cho
2023 J jnl
Latent State Models of Training Dynamics.
Trans. Mach. Learn. Res.
Michael Y. Hu, Angelica Chen, Naomi Saphra, Kyunghyun Cho
2023 A* conf
Linear Connectivity Reveals Generalization Strategies.
ICLR
Jeevesh Juneja, Rachit Bansal, Kyunghyun Cho, João Sedoc, Naomi Saphra
2023 — ed.
Proceedings of the 8th Workshop on Representation Learning for NLP, RepL4NLP@ACL 2023, Toronto, Canada, July 13, 2023.
RepL4NLP@ACL
Burcu Can, Maximilian Mozes, Samuel Cahyawijaya, Naomi Saphra, Nora Kassner, Shauli Ravfogel, Abhilasha Ravichander, Chen Zhao, Isabelle Augenstein, Anna Rogers, Kyunghyun Cho, Edward Grefenstette, Lena Voita
2023 J jnl
Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs.
CoRR
Angelica Chen, Ravid Shwartz-Ziv, Kyunghyun Cho, Matthew L. Leavitt, Naomi Saphra
2023 J jnl
TRAM: Bridging Trust Regions and Sharpness Aware Minimization.
CoRR
Tom Sherborne, Naomi Saphra, Pradeep Dasigi, Hao Peng
2023 J jnl
Towards out-of-distribution generalization in large-scale astronomical surveys: robust networks learn similar representations.
CoRR
Yash Gondhalekar, Sultan Hassan, Naomi Saphra, Sambatra Andrianomena
2022 B conf
Benchmarking Compositionality with Formal Languages.
COLING
Josef Valvoda, Naomi Saphra, Jonathan Rawski, Adina Williams, Ryan Cotterell
2022 J jnl
Learning Transductions to Test Systematic Compositionality.
CoRR
Josef Valvoda, Naomi Saphra, Jonathan Rawski, Ryan Cotterell, Adina Williams
2022 J jnl
Linear Connectivity Reveals Generalization Strategies.
CoRR
Jeevesh Juneja, Rachit Bansal, Kyunghyun Cho, João Sedoc, Naomi Saphra
2022 J jnl
One Venue, Two Conferences: The Separation of Chinese and American Citation Networks.
CoRR
Bingchen Zhao, Yuling Gu, Jessica Zosa Forde, Naomi Saphra
2022 — ed.
Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, BlackboxNLP@EMNLP 2022, Abu Dhabi, United Arab Emirates (Hybrid), December 8, 2022
BlackboxNLP@EMNLP
Jasmijn Bastings, Yonatan Belinkov, Yanai Elazar, Dieuwke Hupkes, Naomi Saphra, Sarah Wiegreffe
2022 J jnl
State-of-the-art generalisation research in NLP: a taxonomy and review.
CoRR
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
2022 A* conf
The MultiBERTs: BERT Reproductions for Robustness Analysis.
ICLR
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
2021 — conf
A Non-Linear Structural Probe.
NAACL-HLT
Jennifer C. White, Tiago Pimentel, Naomi Saphra, Ryan Cotterell
2021 J jnl
A Non-Linear Structural Probe.
CoRR
Jennifer C. White, Tiago Pimentel, Naomi Saphra, Ryan Cotterell
2021 — ed.
Proceedings of the 6th Workshop on Representation Learning for NLP, RepL4NLP@ACL-IJCNLP 2021, Online, August 6, 2021
RepL4NLP@ACL-IJCNLP
Anna Rogers, Iacer Calixto, Ivan Vulic, Naomi Saphra, Nora Kassner, Oana-Maria Camburu, Trapit Bansal, Vered Shwartz
2021 J jnl
The MultiBERTs: BERT Reproductions for Robustness Analysis.
CoRR
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
2020 — conf
LSTMS Compose - and Learn - Bottom-Up.
EMNLP (Findings)
Naomi Saphra, Adam Lopez
2020 J jnl
LSTMs Compose (and Learn) Bottom-Up.
CoRR
Naomi Saphra, Adam Lopez
2020 — conf
Pareto Probing: Trading Off Accuracy for Complexity.
EMNLP (1)
Tiago Pimentel, Naomi Saphra, Adina Williams, Ryan Cotterell
2020 J jnl
Pareto Probing: Trading Off Accuracy for Complexity.
CoRR
Tiago Pimentel, Naomi Saphra, Adina Williams, Ryan Cotterell
2020 A* conf
Understanding Privacy-Related Questions on Stack Overflow.
CHI
Mohammad Tahaei, Kami Vaniea, Naomi Saphra
2020 J jnl
Word Interdependence Exposes How LSTMs Compose Representations.
CoRR
Naomi Saphra, Adam Lopez
2019 J jnl
How to Evaluate Word Representations of Informal Domain?
CoRR
Yekun Chai, Naomi Saphra, Adam Lopez
2019 J jnl
Sparsity Emerges Naturally in Neural Language Models.
CoRR
Naomi Saphra, Adam Lopez
2019 — conf
Understanding Learning Dynamics Of Language Models with SVCCA.
NAACL-HLT (1)
Naomi Saphra, Adam Lopez
2018 — conf
Language Models Learn POS First.
BlackboxNLP@EMNLP
Naomi Saphra, Adam Lopez
2018 J jnl
Understanding Learning Dynamics Of Language Models with SVCCA.
CoRR
Naomi Saphra, Adam Lopez
2017 J jnl
DyNet: The Dynamic Neural Network Toolkit.
CoRR
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
2016 — conf
Evaluating Informal-Domain Word Representations With UrbanDictionary.
RepEval@ACL
Naomi Saphra
2016 J jnl
Evaluating Informal-Domain Word Representations With UrbanDictionary.
CoRR
Naomi Saphra, Adam Lopez
2015 — conf
AMRICA: an AMR Inspector for Cross-language Alignments.
HLT-NAACL
Naomi Saphra, Adam Lopez
2014 A* conf
Understanding Objects in Detail with Fine-Grained Attributes.
CVPR
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
2013 — conf
A Framework for (Under)specifying Dependency Syntax without Overloading Annotators.
LAW@ACL
Nathan Schneider, Brendan O'Connor, Naomi Saphra, David Bamman, Manaal Faruqui, Noah A. Smith, Chris Dyer, Jason Baldridge
2013 J jnl
A framework for (under)specifying dependency syntax without overloading annotators.
CoRR
Nathan Schneider, Brendan O'Connor, Naomi Saphra, David Bamman, Manaal Faruqui, Noah A. Smith, Chris Dyer, Jason Baldridge