{"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/eliciting-transferability-in-multi-task","title":"Eliciting and Understanding Cross-Task Skills with Task-Level Mixture-of-Experts","arxiv_id":"2205.12701","date":"2022-05-25","proceeding":null,"authors":["Qinyuan Ye","Juan Zha","Xiang Ren"],"abstract":"Recent works suggest that transformer models are capable of multi-tasking on diverse NLP tasks and adapting to new tasks efficiently. However, the potential of these multi-task models may be limited as they use the same set of parameters for all tasks. In contrast, humans tackle tasks in a more flexible way, by making proper presumptions on what skills and knowledge are relevant and executing only the necessary computations. Inspired by this, we propose to use task-level mixture-of-expert models, which has a collection of transformer layers (i.e., experts) and a router component that chooses from these experts dynamically and flexibly. We find that these models help improve the average performance gain (ARG) metric by 2.6% when adapting to unseen tasks in the few-shot setting and by 5.6% in the zero-shot generalization setting. Further, we show that the learned routing decisions partly rediscover human categorization of NLP tasks -- certain experts are strongly associated with extractive tasks, some with classification tasks, and some with tasks requiring world knowledge.","url_abs":"https://arxiv.org/abs/2205.12701v2","url_pdf":"https://arxiv.org/pdf/2205.12701v2.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":"eliciting-transferability-in-multi-task","repo_url":"https://github.com/ink-usc/crosstaskmoe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"world-knowledge","task_name":"World Knowledge"},{"task_slug":"zero-shot-generalization","task_name":"Zero-shot Generalization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.12701","atlas_url":"https://app.syntology.ai/?focus=2205.12701","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":"2205.12701"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2205.12701\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2205.12701"},"call":"get_concepts_for_paper(arxiv_id=\"2205.12701\")"}],"by_repo":[{"repo":"ink-usc/crosstaskmoe","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":"b011dc01f0f707c9cf29d7bf721b62a94a3d7754d95b476901c381069d09fc9c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}