Where did you get that? Towards Summarization Attribution for Analysts
Computation and Language
2025-11-13 v1 Artificial Intelligence
Abstract
Analysts require attribution, as nothing can be reported without knowing the source of the information. In this paper, we will focus on automatic methods for attribution, linking each sentence in the summary to a portion of the source text, which may be in one or more documents. We explore using a hybrid summarization, i.e., an automatic paraphrase of an extractive summary, to ease attribution. We also use a custom topology to identify the proportion of different categories of attribution-related errors.
Cite
@article{arxiv.2511.08589,
title = {Where did you get that? Towards Summarization Attribution for Analysts},
author = {Violet B and John M. Conroy and Sean Lynch and Danielle M and Neil P. Molino and Aaron Wiechmann and Julia S. Yang},
journal= {arXiv preprint arXiv:2511.08589},
year = {2025}
}