Naomi Saphra

1. Transcendence: Generative Models Can Outperform The Experts That Train Them
   2024/06/17 by Edwin Zhang, Vincent Zhu, Zhang, Edwin +13 · 8 voices · 9 citations
   #cs.LG #cs.AI
2. DyNet: The Dynamic Neural Network Toolkit
   2017/01/15 by Graham Neubig, Chris Dyer, Neubig, Graham +48 · 2 voices · 14 citations
   Computer Science · Mathematics · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (stat.ML) #Mathematical Software (cs.MS) #Neural Networks and Applications #Time Series Analysis and Forecasting #Topic Modeling #cs.CL #cs.MS #stat.ML
3. Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs
   2023/09/13 by Angelica Chen, Ravid Shwartz-Ziv, Chen, Angelica +7 · 4 voices · 28 citations
   Computer Science · #Topic Modeling #Natural Language Processing Techniques #Explainable Artificial Intelligence (XAI)
4. Mechanistic?
   2024/10/07 by Naomi Saphra, Sarah Wiegreffe, Saphra, Naomi +1 · 3 voices · 8 citations
   Computer Science · #Explainable Artificial Intelligence (XAI) #Multimodal Machine Learning Applications #Adversarial Robustness in Machine Learning
5. Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon
   2024/06/25 by USVSN Sai Prashanth, Prashanth, USVSN Sai, Alvin Deng +23 · 3 voices · 4 citations
   Arts and Humanities · #EFL/ESL Teaching and Learning
6. PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs
   2025/03/12 by Oskar van der Wal, Pietro Lesci, van der Wal, Oskar +11 · 2 voices · 12 citations
   Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques
7. Benchmarks as Microscopes: A Call for Model Metrology
   2024/07/22 by Michael Saxon, Ari Holtzman, Saxon, Michael +7 · 2 voices · 8 citations
   Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Software Engineering (cs.SE) #cs.CL #cs.SE
8. The MultiBERTs: BERT Reproductions for Robustness Analysis
   2021/06/30 by Thibault Sellam, Steve Yadlowsky, Sellam, Thibault +22 · 1 voice · 4 citations
   Computer Science · #Computation and Language (cs.CL) #Data Stream Mining Techniques #FOS: Computer and information sciences #Machine Learning and Algorithms #Topic Modeling #cs.CL
9. Random Scaling of Emergent Capabilities
   2025/02/24 by Rosie Zhao, Tian Qin, Zhao, Rosie +8 · 2 voices · 5 citations
   Decision Sciences · #Complex Systems and Decision Making #cs.LG
10. Latent State Models of Training Dynamics
    2023/08/18 by Michael Y. Hu, Hu, Michael Y., Angelica Chen +5 · 1 voice · 3 citations
    Computer Science · #Neural Networks and Applications
11. Linear Connectivity Reveals Generalization Strategies
    2022/05/24 by Jeevesh Juneja, Juneja, Jeevesh, Rachit Bansal +7 · 1 voice · 2 citations
    Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #cs.CL #cs.LG
12. ChatGPT Doesn't Trust Chargers Fans: Guardrail Sensitivity in Context
    2024/07/09 by Victoria R. Li, Yida Chen, Li, Victoria R. +3 · 1 voice · 3 citations
    Engineering · #Traffic Prediction and Management Techniques #Traffic and Road Safety
13. Hidden Breakthroughs in Language Model Training
    2025/06/18 by Sara Kangaslahti, Elan Rosenfeld, Kangaslahti, Sara +3 · 1 voice · 7 citations
    Computer Science · #cs.LG
14. Can Interpretation Predict Behavior on Unseen Data?
    2025/07/08 by Victoria R. Li, Li, Victoria R., Jenny Kaufmann +8 · 1 voice · 4 citations
    Computer Science · #Adversarial Robustness in Machine Learning #Explainable Artificial Intelligence (XAI) #Machine Learning in Healthcare #cs.AI #cs.CL #cs.LG
15. Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention
    2026/05/28 by Jing Huang, Daniel Wurgaft, Rachit Bansal +6 · 3 voices
    #cs.LG
16. Sometimes I am a Tree: Data Drives Unstable Hierarchical Generalization
    2024/12/05 by Tian Qin, Qin, Tian, Naomi Saphra +3 · 2 voices · 2 citations
    Computer Science · #Computational Physics and Python Applications #Data Analysis with R #Neural Networks and Applications #cs.CL #cs.LG
17. TRAM: Bridging Trust Regions and Sharpness Aware Minimization
    2023/10/05 by Tom Sherborne, Naomi Saphra, Sherborne, Tom +5 · 1 voice · 1 citation
    Computer Science · #Domain Adaptation and Few-Shot Learning #Multimodal Machine Learning Applications #Topic Modeling
18. First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models
    2023/11/08 by Naomi Saphra, Saphra, Naomi, Eve Fleisig +5 · 4 voices
    Social Sciences · #Computational and Text Analysis Methods #cs.CL
19. A Taxonomy of Transcendence
    2025/08/25 by Natalie Abreu, Edwin Zhang, Abreu, Natalie +5 · 3 voices · 2 citations
    #cs.AI
20. Do Activation Verbalization Methods Convey Privileged Information?
    2025/09/16 by Millicent Li, Li, Millicent, Alberto Mario Ceballos Arroyo +8 · 2 voices · 2 citations
    Computer Science · #Natural Language Processing Techniques #Semantic Web and Ontologies #Topic Modeling #cs.CL #cs.LG