activity
20172025
most citedHow Context Affects Language Models' Factual Predictions

80 citations · 94 across the 8 of their papers we have counts for

collaborators

10 papers

cs.CL20227 cited

Towards Fine-grained Causal Reasoning and QA

Linyi Yang, Zhen Wang, Yuxiang Wu +2

Understanding causality is key to the success of NLP applications, especially in high-stakes domains. Causality comes in various perspectives such as enable and prevent that, despi…

cs.CL20222 cited

Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets

Yuxiang Wu, Matt Gardner, Pontus Stenetorp +1

Natural language processing models often exploit spurious correlations between task-independent features and labels in datasets to perform well only within the distributions they a…

cs.CL2021

Training Adaptive Computation for Open-Domain Question Answering with Computational Constraints

Yuxiang Wu, Pasquale Minervini, Pontus Stenetorp +1

Adaptive Computation (AC) has been shown to be effective in improving the efficiency of Open-Domain Question Answering (ODQA) systems. However, current AC approaches require tuning…

cs.CL2021

PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them

Patrick Lewis, Yuxiang Wu, Linqing Liu +5

Open-domain Question Answering models which directly leverage question-answer (QA) pairs, such as closed-book QA (CBQA) models and QA-pair retrievers, show promise in terms of spee…

cs.CL2021

NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned

Sewon Min, Jordan Boyd-Graber, Chris Alberti +50

We review the EfficientQA competition from NeurIPS 2020. The competition focused on open-domain question answering (QA), where systems take natural language questions as input and…

cs.CL20201 cited

Don't Read Too Much into It: Adaptive Computation for Open-Domain Question Answering

Yuxiang Wu, Sebastian Riedel, Pasquale Minervini +1

Most approaches to Open-Domain Question Answering consist of a light-weight retriever that selects a set of candidate passages, and a computationally expensive reader that examines…