Datasets › BookSum

BookSum

Introduced by Wojciech Kryściński et al. in BookSum: A Collection of Datasets for Long-form Narrative Summarization18 May 2021 archive 2025-07-28

BookSum is a collection of datasets for long-form narrative summarization. This dataset covers source documents from the literature domain, such as novels, plays and stories, and includes highly abstractive, human written summaries on three levels of granularity of increasing difficulty: paragraph-, chapter-, and book-level. The domain and structure of this dataset poses a unique set of challenges for summarization systems, which include: processing very long documents, non-trivial causal and temporal dependencies, and rich discourse structures.

BookSum contains summaries for 142,753 paragraphs, 12,293 chapters and 436 books.

Benchmarks archive 2025-07-28

All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Long-Form Narrative Summarization BookSum NexusSum (Mistral Large) BERTScore (F1) 70.70 NexusSum: Hierarchical LLM Agents for Long-Form... — 10 Compare
Text Summarization BookSum Echoes-Extractive-Abstractive ROUGE 42.13 Echoes from Alexandria: A Large Resource for... babelscape/echoes-from-alexandria 3 Compare

Papers archive 2025-07-28

papers with a benchmark row: 6 · with a code link: 3 · where Syntology ran a sample: 0 (0 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran: none of the 6 papers with a benchmark row has a Syntology run on record

Page 1 of 1: papers 1 to 6 of 6 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 39. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

Dataset loaders archive 2025-07-28

2 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

BSD-3 License

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • BookSum

1 variant name, as the archive lists them.

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