{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/long-document-summarization-with-top-down-and-1","title":"Long Document Summarization with Top-down and Bottom-up Inference","arxiv_id":"2203.07586","date":"2022-03-15","proceeding":null,"authors":["Bo Pang","Erik Nijkamp","Wojciech Kryściński","Silvio Savarese","Yingbo Zhou","Caiming Xiong"],"abstract":"Text summarization aims to condense long documents and retain key information. Critical to the success of a summarization model is the faithful inference of latent representations of words or tokens in the source documents. Most recent models infer the latent representations with a transformer encoder, which is purely bottom-up. Also, self-attention-based inference models face the challenge of quadratic complexity with respect to sequence length. We propose a principled inference framework to improve summarization models on these two aspects. Our framework assumes a hierarchical latent structure of a document where the top-level captures the long range dependency at a coarser time scale and the bottom token level preserves the details. Critically, this hierarchical structure enables token representations to be updated in both a bottom-up and top-down manner. In the bottom-up pass, token representations are inferred with local self-attention to leverage its efficiency. Top-down correction is then applied to allow tokens to capture long-range dependency. We demonstrate the effectiveness of the proposed framework on a diverse set of summarization datasets, including narrative, conversational, scientific documents and news. Our model achieves (1) competitive or better performance on short documents with higher memory and compute efficiency, compared to full attention transformers, and (2) state-of-the-art performance on a wide range of long document summarization benchmarks, compared to recent efficient transformers. We also show that our model can summarize an entire book and achieve competitive performance using $0.27\\%$ parameters (464M vs. 175B) and much less training data, compared to a recent GPT-3-based model. These results indicate the general applicability and benefits of the proposed framework.","url_abs":"https://arxiv.org/abs/2203.07586v1","url_pdf":"https://arxiv.org/pdf/2203.07586v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"long-document-summarization-with-top-down-and-1","repo_url":"https://github.com/lllyasviel/framepack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"text-summarization","task_name":"Text Summarization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-summarization-on-arxiv","task":"Text Summarization","dataset":"Arxiv HEP-TH citation graph","model":"Top Down Transformer (AdaPool) (464M)","rank_in_archive_order":1,"of":28,"metrics":{"ROUGE-1":"50.95","ROUGE-2":"21.93","ROUGE-L":"45.61"},"uses_additional_data":false},{"leaderboard":"/sota/text-summarization-on-booksum","task":"Text Summarization","dataset":"BookSum","model":"Top Down Transformer (AdaPool) (464M)","rank_in_archive_order":3,"of":3,"metrics":{"ROUGE":"38.3"},"uses_additional_data":false},{"leaderboard":"/sota/text-summarization-on-pubmed-1","task":"Text Summarization","dataset":"Pubmed","model":"Top Down Transformer (AdaPool) (464M)","rank_in_archive_order":1,"of":29,"metrics":{"ROUGE-1":"51.05","ROUGE-2":"23.26","ROUGE-L":"46.47"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.07586","atlas_url":"https://app.syntology.ai/?focus=2203.07586","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2203.07586"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2203.07586\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2203.07586"},"call":"get_concepts_for_paper(arxiv_id=\"2203.07586\")"}],"by_repo":[{"repo":"lllyasviel/framepack","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2504.12626"],"harvested_for_calls":[{"arxiv_id":"2504.12626","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2504.12626"},"call":"get_harvested_code_for_paper(arxiv_id=\"2504.12626\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"30de548de4a91664998db36949d252ee0c98d8fef4621df850140273dcf5bd31","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}