← Search

Justin Rousseau

2 accepted papers

2023

Less Likely Brainstorming: Using Language Models to Generate Alternative Hypotheses

ACL 2023findings

A human decision-maker benefits the most from an AI assistant that corrects for their biases. For problems such as generating interpretation of a radiology report given findings, a system predicting only highly likely outcomes may be less useful, where such outcomes are already obvious to the user.…

Cited by 10SourcePDFScholar
2023

Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectors

ACL 2023long

The propensity of abstractive summarization models to make factual errors has been studied extensively, including design of metrics to detect factual errors and annotation of errors in current systems’ outputs. However, the ever-evolving nature of summarization systems, metrics, and annotated benchm…