Sewon Min

Efficient and Robust Question Answering from Minimal Context over Documents

2018 · ArXiv.org

Neural models for question answering (QA) over documents have achieved significant performance improvements. Although effective, these models do not scale to large corpora due to their complex modeling of interactions between the document and the …

Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering

2019 · arXiv (Cornell University)

We introduce an approach for open-domain question answering (QA) that retrieves and reads a passage graph, where vertices are passages of text and edges represent relationships that are derived from an external knowledge base or …

Re-Examining Calibration: The Case of Question Answering

2022 · arXiv (Cornell University)

For users to trust model predictions, they need to understand model outputs, particularly their confidence - calibration aims to adjust (calibrate) models' confidence to match expected accuracy. We argue that the traditional calibration evaluation does …

OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens

2025 · arXiv (Cornell University)

We present OLMoTrace, the first system that traces the outputs of language models back to their full, multi-trillion-token training data in real time. OLMoTrace finds and shows verbatim matches between segments of language model output …

Multi-hop Reading Comprehension through Question Decomposition and Rescoring

2019

Multi-hop Reading Comprehension (RC) requires reasoning and aggregation across several paragraphs. We propose a system for multi-hop RC that decomposes a compositional question into simpler sub-questions that can be answered by off-the-shelf single-hop RC models. …

Compositional Questions Do Not Necessitate Multi-hop Reasoning

2019

Multi-hop reading comprehension (RC) questions are challenging because they require reading and reasoning over multiple paragraphs. We argue that it can be difficult to construct large multi-hop RC datasets. For example, even highly compositional questions …

A Discrete Hard EM Approach for Weakly Supervised Question Answering

2019

Sewon Min, Danqi Chen, Hannaneh Hajishirzi, Luke Zettlemoyer. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Dense Passage Retrieval for Open-Domain Question Answering

2020

Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, Wen-tau Yih. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020.

AmbigQA: Answering Ambiguous Open-domain Questions

2020

Ambiguity is inherent to open-domain question answering; especially when exploring new topics, it can be difficult to ask questions that have a single, unambiguous answer. In this paper, we introduce AMBIGQA, a new open-domain question …

Noisy Channel Language Model Prompting for Few-Shot Text Classification

2021 · arXiv (Cornell University)

We introduce a noisy channel approach for language model prompting in few-shot text classification. Instead of computing the likelihood of the label given the input (referred as direct models), channel models compute the conditional probability …

MetaICL: Learning to Learn In Context

2021 · arXiv (Cornell University)

We introduce MetaICL (Meta-training for In-Context Learning), a new meta-training framework for few-shot learning where a pretrained language model is tuned to do in-context learning on a large set of training tasks. This meta-training enables …

Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?

2022

Large language models (LMs) are able to in-context learn—perform a new task via inference alone by conditioning on a few input-label pairs (demonstrations) and making predictions for new inputs. However, there has been little understanding …

FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation

2023

Sewon Min, Kalpesh Krishna, Xinxi Lyu, Mike Lewis, Wen-tau Yih, Pang Koh, Mohit Iyyer, Luke Zettlemoyer, Hannaneh Hajishirzi. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.