Sotabase

Career

· Research Intern, Meta2022–2022
· MS in Computer Science, Columbia University2020–2022
· Ph.D. Candidate, Columbia University2020–
· Research Scientist, OpenAI2019–2020
· Machine Learning Research Engineer, Apple2017–2019
· B.A. in Computer Science, with highest honors, Williams College2013–2017

Publications (48)

Language Models are Few-Shot Learners
Neural Information Processing Systems · 2020
53,522
cited
Outlier Suppression+: Accurate quantization of large language models by equivalent and effective shifting and scaling
Conference on Empirical Methods in Natural Language Processing · 2023
61
cited
SafeText: A Benchmark for Exploring Physical Safety in Language Models
Conference on Empirical Methods in Natural Language Processing · 2022
48
cited
Cord blood T cell subpopulations and associations with maternal cadmium and arsenic exposures
PLoS ONE · 2017
36
cited
Check-COVID: Fact-Checking COVID-19 News Claims with Scientific Evidence
Annual Meeting of the Association for Computational Linguistics · 2023
32
cited
Reading Subtext: Evaluating Large Language Models on Short Story Summarization with Writers
Transactions of the Association for Computational Linguistics · 2024
26
cited
SEA-LION: Southeast Asian Languages in One Network
arXiv.org · 2025
26
cited
Mitigating Covertly Unsafe Text within Natural Language Systems
Conference on Empirical Methods in Natural Language Processing · 2022
13
cited
FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data
Conference on Empirical Methods in Natural Language Processing · 2024
11
cited
STORYSUMM: Evaluating Faithfulness in Story Summarization
Conference on Empirical Methods in Natural Language Processing · 2024
8
cited
Ask Again, Then Fail: Large Language Models’ Vacillations in Judgment
Volume 1 · 2024
6
cited
WebWISE: Unlocking Web Interface Control for LLMs via Sequential Exploration
NAACL-HLT · 2024
6
cited
Unsupervised Selective Rationalization with Noise Injection
Annual Meeting of the Association for Computational Linguistics · 2023
5
cited
Towards Detecting Harmful Agendas in News Articles
Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis · 2023
4
cited
GenEARL: A Training-Free Generative Framework for Multimodal Event Argument Role Labeling
arXiv.org · 2024
3
cited
AdvSumm: Adversarial Training for Bias Mitigation in Text Summarization
Proceedings of The 5th New Frontiers in Summarization Workshop · 2025
2
cited
Assay2Mol: Large Language Model-based Drug Design Using BioAssay Context
Conference on Empirical Methods in Natural Language Processing · 2025
2
cited
Assessing biomedical knowledge robustness in large language models by query-efficient sampling attacks
Trans. Mach. Learn. Res. · 2024
2
cited
Counterfactual Simulatability of LLM Explanations for Generation Tasks
arXiv.org · 2025
2
cited
Guiding LLM Decision-Making with Fairness Reward Models
arXiv.org · 2025
2
cited
Sotabase
Melanie Subbiah | Researcher Profile | Sotabase | Sotabase