Browse State-of-the-Art › Long-Form Narrative Summarization

Long-Form Narrative Summarization

4 papers with code · 4 benchmarks · 3 datasets archive 2025-07-28

Knowledge BaseNatural Language Processing

Summarizing long-form narratives, such as books, movies, and TV scripts, remains an open challenge in NLP. Unlike news or document summarization, narratives require capturing intricate plotlines, evolving character relationships, and thematic coherence over tens of thousands of tokens. The hybrid structure of narratives, which combines descriptive prose with multi-speaker dialogues, implicit inference, and dynamic topic shifts, adds further complexity, demanding an approach that preserves contextual integrity while condensing information effectively. Furthermore, the sheer length of narrative texts, typically ranging from 40K to 160K tokens, poses significant challenges for standard summarization models.

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

4 leaderboard tables shown for this task, 4 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
BookSum (10 rows) NexusSum (Mistral Large) NexusSum: Hierarchical LLM Agents for Long-Form Narrative Summarization — — Compare
MENSA (10 rows) NexusSum (Mistral Large) NexusSum: Hierarchical LLM Agents for Long-Form Narrative Summarization — — Compare
SummScreen (5 rows) NexusSum (Mistral Large) NexusSum: Hierarchical LLM Agents for Long-Form Narrative Summarization — — Compare
MovieSum (5 rows) NexusSum (Mistral Large) NexusSum: Hierarchical LLM Agents for Long-Form Narrative Summarization — — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

3 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

4 shown of 4 papers with code (8 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

Syntology lines on 2 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.

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