{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/skeleton-of-thought-large-language-models-can","title":"Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation","arxiv_id":"2307.15337","date":"2023-07-28","proceeding":null,"authors":["Xuefei Ning","Zinan Lin","Zixuan Zhou","Zifu Wang","Huazhong Yang","Yu Wang"],"abstract":"This work aims at decreasing the end-to-end generation latency of large language models (LLMs). One of the major causes of the high generation latency is the sequential decoding approach adopted by almost all state-of-the-art LLMs. In this work, motivated by the thinking and writing process of humans, we propose Skeleton-of-Thought (SoT), which first guides LLMs to generate the skeleton of the answer, and then conducts parallel API calls or batched decoding to complete the contents of each skeleton point in parallel. Not only does SoT provide considerable speed-ups across 12 LLMs, but it can also potentially improve the answer quality on several question categories. SoT is an initial attempt at data-centric optimization for inference efficiency, and showcases the potential of eliciting high-quality answers by explicitly planning the answer structure in language.","url_abs":"https://arxiv.org/abs/2307.15337v3","url_pdf":"https://arxiv.org/pdf/2307.15337v3.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":"skeleton-of-thought-large-language-models-can","repo_url":"https://github.com/imagination-research/sot","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2307.15337","atlas_url":"https://app.syntology.ai/?focus=2307.15337","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.15337"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/imagination-research/sot","reach":null}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"38d170ad2615dbe1","entry":"OutlineScheduler","repo":"imagination-research/sot","repo_kind":"official","path":"sot/schedulers/outline_scheduler.py","file_url":"https://github.com/imagination-research/sot/blob/HEAD/sot/schedulers/outline_scheduler.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"38d170ad2615dbe1"}},{"code_sha256_prefix":"4b11415e0b05cbc2","entry":"Scheduler","repo":"imagination-research/sot","repo_kind":"official","path":"sot/schedulers/outline_scheduler.py","file_url":"https://github.com/imagination-research/sot/blob/HEAD/sot/schedulers/outline_scheduler.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4b11415e0b05cbc2"}},{"code_sha256_prefix":"630357dce5fe6032","entry":"_print_to_streams","repo":"imagination-research/sot","repo_kind":"official","path":"sot/schedulers/outline_scheduler.py","file_url":"https://github.com/imagination-research/sot/blob/HEAD/sot/schedulers/outline_scheduler.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"630357dce5fe6032"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}