Enhancing Long Document Long Form Summarisation with Self-Planning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Du, Xiaotang, Saxena, Rohit, Perez-Beltrachini, Laura, Minervini, Pasquale, Titov, Ivan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909970713280512
author Du, Xiaotang
Saxena, Rohit
Perez-Beltrachini, Laura
Minervini, Pasquale
Titov, Ivan
author_facet Du, Xiaotang
Saxena, Rohit
Perez-Beltrachini, Laura
Minervini, Pasquale
Titov, Ivan
contents We introduce a novel approach for long context summarisation, highlight-guided generation, that leverages sentence-level information as a content plan to improve the traceability and faithfulness of generated summaries. Our framework applies self-planning methods to identify important content and then generates a summary conditioned on the plan. We explore both an end-to-end and two-stage variants of the approach, finding that the two-stage pipeline performs better on long and information-dense documents. Experiments on long-form summarisation datasets demonstrate that our method consistently improves factual consistency while preserving relevance and overall quality. On GovReport, our best approach has improved ROUGE-L by 4.1 points and achieves about 35% gains in SummaC scores. Qualitative analysis shows that highlight-guided summarisation helps preserve important details, leading to more accurate and insightful summaries across domains.
format Preprint
id arxiv_https___arxiv_org_abs_2512_17179
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Long Document Long Form Summarisation with Self-Planning
Du, Xiaotang
Saxena, Rohit
Perez-Beltrachini, Laura
Minervini, Pasquale
Titov, Ivan
Computation and Language
We introduce a novel approach for long context summarisation, highlight-guided generation, that leverages sentence-level information as a content plan to improve the traceability and faithfulness of generated summaries. Our framework applies self-planning methods to identify important content and then generates a summary conditioned on the plan. We explore both an end-to-end and two-stage variants of the approach, finding that the two-stage pipeline performs better on long and information-dense documents. Experiments on long-form summarisation datasets demonstrate that our method consistently improves factual consistency while preserving relevance and overall quality. On GovReport, our best approach has improved ROUGE-L by 4.1 points and achieves about 35% gains in SummaC scores. Qualitative analysis shows that highlight-guided summarisation helps preserve important details, leading to more accurate and insightful summaries across domains.
title Enhancing Long Document Long Form Summarisation with Self-Planning
topic Computation and Language
url https://arxiv.org/abs/2512.17179