{"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/investigating-efficiently-extending","title":"Investigating Efficiently Extending Transformers for Long Input Summarization","arxiv_id":"2208.04347","date":"2022-08-08","proceeding":null,"authors":["Jason Phang","Yao Zhao","Peter J. Liu"],"abstract":"While large pretrained Transformer models have proven highly capable at tackling natural language tasks, handling long sequence inputs continues to be a significant challenge. One such task is long input summarization, where inputs are longer than the maximum input context of most pretrained models. Through an extensive set of experiments, we investigate what model architectural changes and pretraining paradigms can most efficiently adapt a pretrained Transformer for long input summarization. We find that a staggered, block-local Transformer with global encoder tokens strikes a good balance of performance and efficiency, and that an additional pretraining phase on long sequences meaningfully improves downstream summarization performance. Based on our findings, we introduce PEGASUS-X, an extension of the PEGASUS model with additional long input pretraining to handle inputs of up to 16K tokens. PEGASUS-X achieves strong performance on long input summarization tasks comparable with much larger models while adding few additional parameters and not requiring model parallelism to train.","url_abs":"https://arxiv.org/abs/2208.04347v1","url_pdf":"https://arxiv.org/pdf/2208.04347v1.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":"investigating-efficiently-extending","repo_url":"https://github.com/google-research/pegasus","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"investigating-efficiently-extending","repo_url":"https://github.com/MindCode-4/code-2/tree/main/pegasus_x","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"16k","task_name":"16k"},{"task_slug":"long-range-modeling","task_name":"Long-range modeling"},{"task_slug":"text-summarization","task_name":"Text Summarization"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"pegasus","method_name":"PEGASUS"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/long-range-modeling-on-scrolls","task":"Long-range modeling","dataset":"SCROLLS","model":"PEGASUS-X","rank_in_archive_order":11,"of":13,"metrics":{"GovRep":"60.3 / 30.0 / 31.5","QMSum":"33.2 / 9.6 / 21.6 ","SumScr":"35.7 / 9.1 / 20.6"},"uses_additional_data":false},{"leaderboard":"/sota/long-range-modeling-on-scrolls","task":"Long-range modeling","dataset":"SCROLLS","model":"PEGASUS-X-Base","rank_in_archive_order":12,"of":13,"metrics":{"GovRep":"59.3 / 29.3 / 30.9","QMSum":"32.9 / 9.8 / 21.4","SumScr":" 35.0 / 8.9 / 20.4"},"uses_additional_data":false},{"leaderboard":"/sota/text-summarization-on-arxiv","task":"Text Summarization","dataset":"Arxiv HEP-TH citation graph","model":"Pegasus-X","rank_in_archive_order":3,"of":28,"metrics":{"ROUGE-1":"50.0","ROUGE-2":"21.8","ROUGE-L":"44.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2208.04347","atlas_url":"https://app.syntology.ai/?focus=2208.04347","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":"2208.04347"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2208.04347\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2208.04347"},"call":"get_concepts_for_paper(arxiv_id=\"2208.04347\")"}],"by_repo":[{"repo":"google-research/pegasus","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1912.08777"],"harvested_for_calls":[{"arxiv_id":"1912.08777","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1912.08777"},"call":"get_harvested_code_for_paper(arxiv_id=\"1912.08777\")"}]},{"repo":"MindCode-4/code-2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"8637e9da8465b43cc5f958dec08aad59bb75f2458e19073bf059c9fda78345ba","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}