English

Open Domain Multi-document Summarization: A Comprehensive Study of Model Brittleness under Retrieval

Computation and Language 2023-10-26 v3 Artificial Intelligence

Abstract

Multi-document summarization (MDS) assumes a set of topic-related documents are provided as input. In practice, this document set is not always available; it would need to be retrieved given an information need, i.e. a question or topic statement, a setting we dub "open-domain" MDS. We study this more challenging setting by formalizing the task and bootstrapping it using existing datasets, retrievers and summarizers. Via extensive automatic and human evaluation, we determine: (1) state-of-the-art summarizers suffer large reductions in performance when applied to open-domain MDS, (2) additional training in the open-domain setting can reduce this sensitivity to imperfect retrieval, and (3) summarizers are insensitive to the retrieval of duplicate documents and the order of retrieved documents, but highly sensitive to other errors, like the retrieval of irrelevant documents. Based on our results, we provide practical guidelines to enable future work on open-domain MDS, e.g. how to choose the number of retrieved documents to summarize. Our results suggest that new retrieval and summarization methods and annotated resources for training and evaluation are necessary for further progress in the open-domain setting.

Keywords

Cite

@article{arxiv.2212.10526,
  title  = {Open Domain Multi-document Summarization: A Comprehensive Study of Model Brittleness under Retrieval},
  author = {John Giorgi and Luca Soldaini and Bo Wang and Gary Bader and Kyle Lo and Lucy Lu Wang and Arman Cohan},
  journal= {arXiv preprint arXiv:2212.10526},
  year   = {2023}
}

Comments

Accepted to EMNLP Findings 2023

R2 v1 2026-06-28T07:45:22.688Z