Sotabase

Career

· PhD in Computer Science, UC Berkeley2022–

Publications (114)

GPT-4o System Card
arXiv.org · 2024
2,980
cited
Extracting Training Data from Large Language Models
USENIX Security Symposium · 2020
2,566
cited
Calibrate Before Use: Improving Few-Shot Performance of Language Models
International Conference on Machine Learning · 2021
1,708
cited
Universal Adversarial Triggers for Attacking and Analyzing NLP
Conference on Empirical Methods in Natural Language Processing · 2019
996
cited
InCoder: A Generative Model for Code Infilling and Synthesis
International Conference on Learning Representations · 2022
817
cited
Large Language Models Struggle to Learn Long-Tail Knowledge
International Conference on Machine Learning · 2022
561
cited
Fabry disease revisited: Management and treatment recommendations for adult patients.
Molecular Genetics and Metabolism · 2018
532
cited
Scalable Extraction of Training Data from (Production) Language Models
arXiv.org · 2023
484
cited
Pretrained Transformers Improve Out-of-Distribution Robustness
Annual Meeting of the Association for Computational Linguistics · 2020
469
cited
Evaluating Models’ Local Decision Boundaries via Contrast Sets
Findings · 2020
422
cited
Deduplicating Training Data Mitigates Privacy Risks in Language Models
International Conference on Machine Learning · 2022
369
cited
gpt-oss-120b&gpt-oss-20b Model Card
2025
357
cited
Poisoning Language Models During Instruction Tuning
International Conference on Machine Learning · 2023
282
cited
The False Promise of Imitating Proprietary LLMs
arXiv.org · 2023
256
cited
Concealed Data Poisoning Attacks on NLP Models
North American Chapter of the Association for Computational Linguistics · 2021
199
cited
Deliberative Alignment: Reasoning Enables Safer Language Models
Robotics · 2024
199
cited
Train Big, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers
International Conference on Machine Learning · 2020
173
cited
Compositional Questions Do Not Necessitate Multi-hop Reasoning
Annual Meeting of the Association for Computational Linguistics · 2019
160
cited
Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers
arXiv.org · 2020
153
cited
AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models
Conference on Empirical Methods in Natural Language Processing · 2019
144
cited
Sotabase
Eric Wallace | Researcher Profile | Sotabase | Sotabase