{"url":"/task/long-form-narrative-summarization","name":"Long-Form Narrative Summarization","slug":"long-form-narrative-summarization","description_markdown":"Summarizing long-form narratives, such as books,\r\nmovies, 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\r\nnarratives, which combines descriptive prose with\r\nmulti-speaker dialogues, implicit inference, and dynamic topic shifts, adds further complexity, demanding an approach that preserves contextual integrity\r\nwhile condensing information effectively. Furthermore, the sheer length of narrative texts, typically\r\nranging from 40K to 160K tokens, poses significant challenges for standard summarization models.","categories":[{"name":"Knowledge Base","url":"/area/knowledge-base"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":8,"papers_with_code":4,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/long-form-narrative-summarization-on-booksum","slug":"long-form-narrative-summarization-on-booksum","dataset":"BookSum","dataset_url":"/dataset/booksum","rows_in_archive":10,"metrics":["BERTScore (F1)","ROUGE-1","ROUGE-2","ROUGE-L","ROUGE (geometric mean of 1/2/L)"],"first_row_in_archive_order":{"model":"NexusSum (Mistral Large)","paper_title":"NexusSum: Hierarchical LLM Agents for Long-Form Narrative Summarization","paper_url":"/paper/nexussum-hierarchical-llm-agents-for-long","paper_date":"2025-05-30","arxiv_id":"2505.24575","code_links":[],"syntology":null}},{"leaderboard":"/sota/long-form-narrative-summarization-on-mensa","slug":"long-form-narrative-summarization-on-mensa","dataset":"MENSA","dataset_url":"/dataset/mensa","rows_in_archive":10,"metrics":["BERTScore (F1)","ROUGE-1","ROUGE-2","ROUGE-L"],"first_row_in_archive_order":{"model":"NexusSum (Mistral Large)","paper_title":"NexusSum: Hierarchical LLM Agents for Long-Form Narrative Summarization","paper_url":"/paper/nexussum-hierarchical-llm-agents-for-long","paper_date":"2025-05-30","arxiv_id":"2505.24575","code_links":[],"syntology":null}},{"leaderboard":"/sota/long-form-narrative-summarization-on","slug":"long-form-narrative-summarization-on","dataset":"SummScreen","dataset_url":"/dataset/summscreen","rows_in_archive":5,"metrics":["BERTScore (F1)","ROUGE-1","ROUGE-2","ROUGE-L"],"first_row_in_archive_order":{"model":"NexusSum (Mistral Large)","paper_title":"NexusSum: Hierarchical LLM Agents for Long-Form Narrative Summarization","paper_url":"/paper/nexussum-hierarchical-llm-agents-for-long","paper_date":"2025-05-30","arxiv_id":"2505.24575","code_links":[],"syntology":null}},{"leaderboard":"/sota/long-form-narrative-summarization-on-moviesum","slug":"long-form-narrative-summarization-on-moviesum","dataset":"MovieSum","dataset_url":null,"rows_in_archive":5,"metrics":["BERTScore (F1)","ROUGE-1","ROUGE-2","ROUGE-L"],"first_row_in_archive_order":{"model":"NexusSum (Mistral Large)","paper_title":"NexusSum: Hierarchical LLM Agents for Long-Form Narrative Summarization","paper_url":"/paper/nexussum-hierarchical-llm-agents-for-long","paper_date":"2025-05-30","arxiv_id":"2505.24575","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/summscreen","name":"SummScreen","full_name":"","num_papers_in_archive":60},{"url":"/dataset/booksum","name":"BookSum","full_name":"","num_papers_in_archive":39},{"url":"/dataset/mensa","name":"MENSA","full_name":"Movie Scene Saliency Dataset","num_papers_in_archive":4}],"subtasks":[],"parent_tasks":[{"url":"/task/text-summarization","name":"Text Summarization"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":4,"of":4,"tagged_in_all":8,"items":[{"url":"/paper/booksum-a-collection-of-datasets-for-long","title":"BookSum: A Collection of Datasets for Long-form Narrative Summarization","date":"2021-05-18","arxiv_id":"2105.08209","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/agent-as-judge-for-factual-summarization-of","title":"Agent-as-Judge for Factual Summarization of Long Narratives","date":"2025-01-17","arxiv_id":"2501.09993","repositories_listed":1,"syntology":{"n":13,"n_ran":0,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/moviesum-an-abstractive-summarization-dataset","title":"MovieSum: An Abstractive Summarization Dataset for Movie Screenplays","date":"2024-08-12","arxiv_id":"2408.06281","repositories_listed":1,"syntology":null},{"url":"/paper/select-and-summarize-scene-saliency-for-movie","title":"Select and Summarize: Scene Saliency for Movie Script Summarization","date":"2024-04-04","arxiv_id":"2404.03561","repositories_listed":1,"syntology":null}],"syntology_records":2,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}