Sotabase

Career

· Associate Faculty, Columbia University2025–
· Master of Science - MS, Architecture, Columbia University2024–2025
· Architectural Designer, Mass Studies2018–2023
· Bachelor's degree, Architecture, Seoul National University2011–2016

Publications (78)

Dense Passage Retrieval for Open-Domain Question Answering
Conference on Empirical Methods in Natural Language Processing · 2020
4,964
cited
Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?
Conference on Empirical Methods in Natural Language Processing · 2022
1,843
cited
FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation
Conference on Empirical Methods in Natural Language Processing · 2023
1,043
cited
Measuring and Narrowing the Compositionality Gap in Language Models
Conference on Empirical Methods in Natural Language Processing · 2022
990
cited
REPLUG: Retrieval-Augmented Black-Box Language Models
North American Chapter of the Association for Computational Linguistics · 2023
872
cited
UnifiedQA: Crossing Format Boundaries With a Single QA System
Findings · 2020
801
cited
MetaICL: Learning to Learn In Context
North American Chapter of the Association for Computational Linguistics · 2021
578
cited
AmbigQA: Answering Ambiguous Open-domain Questions
Conference on Empirical Methods in Natural Language Processing · 2020
407
cited
Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters
Annual Meeting of the Association for Computational Linguistics · 2022
337
cited
Multi-hop Reading Comprehension through Question Decomposition and Rescoring
Annual Meeting of the Association for Computational Linguistics · 2019
262
cited
Noisy Channel Language Model Prompting for Few-Shot Text Classification
Annual Meeting of the Association for Computational Linguistics · 2021
233
cited
A Discrete Hard EM Approach for Weakly Supervised Question Answering
Conference on Empirical Methods in Natural Language Processing · 2019
169
cited
Efficient and Robust Question Answering from Minimal Context over Documents
Annual Meeting of the Association for Computational Linguistics · 2018
168
cited
Do Membership Inference Attacks Work on Large Language Models?
arXiv.org · 2024
166
cited
OLMoE: Open Mixture-of-Experts Language Models
arXiv.org · 2024
164
cited
Compositional Questions Do Not Necessitate Multi-hop Reasoning
Annual Meeting of the Association for Computational Linguistics · 2019
160
cited
Efficient One-Pass End-to-End Entity Linking for Questions
Conference on Empirical Methods in Natural Language Processing · 2020
157
cited
Retrieval-based Language Models and Applications
Annual Meeting of the Association for Computational Linguistics · 2023
132
cited
Question Answering through Transfer Learning from Large Fine-grained Supervision Data
Annual Meeting of the Association for Computational Linguistics · 2017
121
cited
Spurious Rewards: Rethinking Training Signals in RLVR
arXiv.org · 2025
118
cited
Sotabase
Sewon Min | Researcher Profile | Sotabase | Sotabase