Papers › Factorizing Content and Budget Decisions in Abstractive Summarization of Long Documents
Factorizing Content and Budget Decisions in Abstractive Summarization of Long Documents
Marcio Fonseca, Yftah Ziser, Shay B. Cohen
We argue that disentangling content selection from the budget used to cover salient content improves the performance and applicability of abstractive summarizers. Our method, FactorSum, does this disentanglement by factorizing summarization into two steps through an energy function: (1) generation of abstractive summary views; (2) combination of these views into a final summary, following a budget and content guidance. This guidance may come from different sources, including from an advisor model such as BART or BigBird, or in oracle mode -- from the reference. This factorization achieves significantly higher ROUGE scores on multiple benchmarks for long document summarization, namely PubMed, arXiv, and GovReport. Most notably, our model is effective for domain adaptation. When trained only on PubMed samples, it achieves a 46.29 ROUGE-1 score on arXiv, which indicates a strong performance due to more flexible budget adaptation and content selection less dependent on domain-specific textual structure.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Text Summarization | Arxiv HEP-TH citation graph | FactorSum | ROUGE-1 | 49.32 | #5 of 28 | Archive leaderboard | report |
| Text Summarization | Arxiv HEP-TH citation graph | FactorSum | ROUGE-2 | 20.27 | #5 of 28 | Archive leaderboard | report |
| Text Summarization | Arxiv HEP-TH citation graph | FactorSum | ROUGE-L | 44.76 | #5 of 28 | Archive leaderboard | report |
| Text Summarization | GovReport | FactorSum | ROUGE-1 | 60.1 | #1 of 2 | Archive leaderboard | report |
| Text Summarization | GovReport | FactorSum | ROUGE-2 | 25.28 | #1 of 2 | Archive leaderboard | report |
| Text Summarization | GovReport | FactorSum | ROUGE-L | 56.65 | #1 of 2 | Archive leaderboard | report |
| Text Summarization | Pubmed | FactorSum | ROUGE-1 | 47.5 | #12 of 29 | Archive leaderboard | report |
| Text Summarization | Pubmed | FactorSum | ROUGE-2 | 20.33 | #12 of 29 | Archive leaderboard | report |
| Text Summarization | Pubmed | FactorSum | ROUGE-L | 43.76 | #12 of 29 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
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