Sewon Min

DS SERVE: A Framework for Efficient and Scalable Neural Retrieval AAAI 2026 A Novel Multi-Document Retrieval Benchmark: Journalist Source-Selection in Newswriting NAACL 2025 OLMoE: Open Mixture-of-Experts Language Models ICLR 2025 OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens ACL 2025 Organize the Web: Constructing Domains Enhances Pre-Training Data Curation ICML 2025 BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models ICLR 2024 CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation EMNLP 2024 In-Context Pretraining: Language Modeling Beyond Document Boundaries ICLR 2024 REPLUG: Retrieval-Augmented Black-Box Language Models NAACL 2024 Scaling Retrieval-Based Language Models with a Trillion-Token Datastore NeurIPS 2024 SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore ICLR 2024 CREPE: Open-Domain Question Answering with False Presuppositions ACL 2023 FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation EMNLP 2023 Measuring and Narrowing the Compositionality Gap in Language Models EMNLP 2023 Nonparametric Masked Language Modeling ACL 2023 Retrieval-based Language Models and Applications ACL 2023 Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters ACL 2023 Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations ACL 2023 Exploring The Landscape of Distributional Robustness for Question Answering Models EMNLP 2022 FaVIQ: FAct Verification from Information-seeking Questions ACL 2022 MetaICL: Learning to Learn In Context NAACL 2022 Noisy Channel Language Model Prompting for Few-Shot Text Classification ACL 2022 Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts NAACL 2022 Re-Examining Calibration: The Case of Question Answering EMNLP 2022 Rethinking the Role of Demonstrations: What Makes In-Context Learning Work? EMNLP 2022 Zero- and Few-Shot NLP with Pretrained Language Models ACL 2022 Beyond Paragraphs: NLP for Long Sequences NAACL 2021 Joint Passage Ranking for Diverse Multi-Answer Retrieval EMNLP 2021 RECONSIDER: Improved Re-Ranking using Span-Focused Cross-Attention for Open Domain Question Answering NAACL 2021 AmbigQA: Answering Ambiguous Open-domain Questions EMNLP 2020 Dense Passage Retrieval for Open-Domain Question Answering EMNLP 2020 Efficient One-Pass End-to-End Entity Linking for Questions EMNLP 2020 UNIFIEDQA: Crossing Format Boundaries with a Single QA System EMNLP 2020 A Discrete Hard EM Approach for Weakly Supervised Question Answering EMNLP 2019 Compositional Questions Do Not Necessitate Multi-hop Reasoning ACL 2019 Multi-hop Reading Comprehension through Question Decomposition and Rescoring ACL 2019 On Making Reading Comprehension More Comprehensive EMNLP 2019 Efficient and Robust Question Answering from Minimal Context over Documents ACL 2018 Neural Speed Reading via Skim-RNN ICLR 2018 Question Answering through Transfer Learning from Large Fine-grained Supervision Data ACL 2017