Enhancing Long Document Long Form Summarisation with Self-Planning

ACL ARR 2025 July Submission1013 Authors

Abstract: 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 achieves up to 4.1 improvement in ROUGE-L and 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.

Paper Type: Short

Research Area: Summarization

Research Area Keywords: Summarization, Generation

Languages Studied: English

Previous URL: https://openreview.net/forum?id=054mn5QqFV

Reassignment Request Area Chair: Yes, I want a different area chair for our submission

Reassignment Request Reviewers: Yes, I want a different set of reviewers

A1 Limitations Section: This paper has a limitations section.

A2 Potential Risks: N/A

B Use Or Create Scientific Artifacts: Yes

B1 Cite Creators Of Artifacts: Yes

B1 Elaboration: Appendix A

B2 Discuss The License For Artifacts: Yes

B2 Elaboration: Appendix A

B3 Artifact Use Consistent With Intended Use: N/A

B4 Data Contains Personally Identifying Info Or Offensive Content: N/A

B5 Documentation Of Artifacts: N/A

B6 Statistics For Data: Yes

B6 Elaboration: Appendix A

C Computational Experiments: Yes

C1 Model Size And Budget: Yes

C1 Elaboration: Appendix C

C2 Experimental Setup And Hyperparameters: Yes

C2 Elaboration: Section 5

C3 Descriptive Statistics: N/A

C4 Parameters For Packages: Yes

C4 Elaboration: Section 5

D Human Subjects Including Annotators: No

D1 Instructions Given To Participants: N/A

D2 Recruitment And Payment: N/A

D3 Data Consent: N/A

D4 Ethics Review Board Approval: N/A

D5 Characteristics Of Annotators: N/A

E Ai Assistants In Research Or Writing: Yes

E1 Information About Use Of Ai Assistants: Yes

E1 Elaboration: We used AI assistants to check the fluency and grammaticality of our manuscript, and to help with latex formatting and the implementation of post-processing scripts and interfaces for qualitative analyses.

Author Submission Checklist: yes

Submission Number: 1013