{"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/task-compass-scaling-multi-task-pre-training","title":"Task Compass: Scaling Multi-task Pre-training with Task Prefix","arxiv_id":"2210.06277","date":"2022-10-12","proceeding":null,"authors":["Zhuosheng Zhang","Shuohang Wang","Yichong Xu","Yuwei Fang","Wenhao Yu","Yang Liu","Hai Zhao","Chenguang Zhu","Michael Zeng"],"abstract":"Leveraging task-aware annotated data as supervised signals to assist with self-supervised learning on large-scale unlabeled data has become a new trend in pre-training language models. Existing studies show that multi-task learning with large-scale supervised tasks suffers from negative effects across tasks. To tackle the challenge, we propose a task prefix guided multi-task pre-training framework to explore the relationships among tasks. We conduct extensive experiments on 40 datasets, which show that our model can not only serve as the strong foundation backbone for a wide range of tasks but also be feasible as a probing tool for analyzing task relationships. The task relationships reflected by the prefixes align transfer learning performance between tasks. They also suggest directions for data augmentation with complementary tasks, which help our model achieve human-parity results on commonsense reasoning leaderboards. Code is available at https://github.com/cooelf/CompassMTL","url_abs":"https://arxiv.org/abs/2210.06277v1","url_pdf":"https://arxiv.org/pdf/2210.06277v1.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":"task-compass-scaling-multi-task-pre-training","repo_url":"https://github.com/cooelf/compassmtl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"sentence-completion","task_name":"Sentence Completion"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/common-sense-reasoning-on-winogrande","task":"Common Sense Reasoning","dataset":"WinoGrande","model":"CompassMTL 567M with Tailor","rank_in_archive_order":3,"of":77,"metrics":{"Accuracy":"90.5"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-winogrande","task":"Common Sense Reasoning","dataset":"WinoGrande","model":"CompassMTL 567M","rank_in_archive_order":4,"of":77,"metrics":{"Accuracy":"89.6"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-winogrande","task":"Common Sense Reasoning","dataset":"WinoGrande","model":"ExDeBERTa 567M","rank_in_archive_order":8,"of":77,"metrics":{"Accuracy":"87"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-piqa","task":"Question Answering","dataset":"PIQA","model":"CompassMTL 567M with Tailor","rank_in_archive_order":3,"of":67,"metrics":{"Accuracy":"88.3"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-piqa","task":"Question Answering","dataset":"PIQA","model":"CompassMTL 567M","rank_in_archive_order":6,"of":67,"metrics":{"Accuracy":"87.3"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-piqa","task":"Question Answering","dataset":"PIQA","model":"ExDeBERTa 567M","rank_in_archive_order":10,"of":67,"metrics":{"Accuracy":"85.5"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-social-iqa","task":"Question Answering","dataset":"SIQA","model":"CompassMTL 567M with Tailor","rank_in_archive_order":3,"of":24,"metrics":{"Accuracy":"82.2"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-social-iqa","task":"Question Answering","dataset":"SIQA","model":"CompassMTL 567M","rank_in_archive_order":4,"of":24,"metrics":{"Accuracy":"81.7"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-social-iqa","task":"Question Answering","dataset":"SIQA","model":"ExDeBERTa 567M","rank_in_archive_order":9,"of":24,"metrics":{"Accuracy":"79.6"},"uses_additional_data":false},{"leaderboard":"/sota/sentence-completion-on-hellaswag","task":"Sentence Completion","dataset":"HellaSwag","model":"CompassMTL 567M with Tailor","rank_in_archive_order":1,"of":89,"metrics":{"Accuracy":"96.1"},"uses_additional_data":false},{"leaderboard":"/sota/sentence-completion-on-hellaswag","task":"Sentence Completion","dataset":"HellaSwag","model":"CompassMTL 567M","rank_in_archive_order":2,"of":89,"metrics":{"Accuracy":"95.6"},"uses_additional_data":false},{"leaderboard":"/sota/sentence-completion-on-hellaswag","task":"Sentence Completion","dataset":"HellaSwag","model":"ExDeBERTa 567M","rank_in_archive_order":31,"of":89,"metrics":{"Accuracy":"83.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.06277","atlas_url":"https://app.syntology.ai/?focus=2210.06277","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":"2210.06277"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2210.06277\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2210.06277"},"call":"get_concepts_for_paper(arxiv_id=\"2210.06277\")"}],"by_repo":[{"repo":"cooelf/compassmtl","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"b96c8d6fddf01c895ba7dfae2228acd3b699fac6d3105bcfd29eae3f0d57c23f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}