Papers › Unsupervised Summarization Re-ranking

Unsupervised Summarization Re-ranking

19 Dec 2022arXiv:2212.09593archive 2025-07-28

Mathieu Ravaut, Shafiq Joty, Nancy Chen

With the rise of task-specific pre-training objectives, abstractive summarization models like PEGASUS offer appealing zero-shot performance on downstream summarization tasks. However, the performance of such unsupervised models still lags significantly behind their supervised counterparts. Similarly to the supervised setup, we notice a very high variance in quality among summary candidates from these models while only one candidate is kept as the summary output. In this paper, we propose to re-rank summary candidates in an unsupervised manner, aiming to close the performance gap between unsupervised and supervised models. Our approach improves the unsupervised PEGASUS by up to 7.27% and ChatGPT by up to 6.86% relative mean ROUGE across four widely-adopted summarization benchmarks ; and achieves relative gains of 7.51% (up to 23.73% from XSum to WikiHow) averaged over 30 zero-shot transfer setups (finetuning on a dataset, evaluating on another).

PaperPDFCode

Code

ntunlp/summscore officialmentioned in papermentioned on GitHubpytorch report
ntunlp/summscore-acl-findings-2023 officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Abstractive Text SummarizationRe-Ranking

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

PEGASUS

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections