{"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/z-icl-zero-shot-in-context-learning-with","title":"Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations","arxiv_id":"2212.09865","date":"2022-12-19","proceeding":null,"authors":["Xinxi Lyu","Sewon Min","Iz Beltagy","Luke Zettlemoyer","Hannaneh Hajishirzi"],"abstract":"Although large language models can be prompted for both zero- and few-shot learning, performance drops significantly when no demonstrations are available. In this paper, we introduce Z-ICL, a new zero-shot method that closes the gap by constructing pseudo-demonstrations for a given test input using a raw text corpus. Concretely, pseudo-demonstrations are constructed by (1) finding the nearest neighbors to the test input from the corpus and pairing them with random task labels, and (2) applying a set of techniques to reduce the amount of direct copying the model does from the resulting demonstrations. Evaluation on nine classification datasets shows that Z-ICL outperforms previous zero-shot methods by a significant margin, and is on par with in-context learning with labeled training data in the few-shot setting. Overall, Z-ICL provides a significantly higher estimate of the zero-shot performance levels of a model, and supports future efforts to develop better pseudo-demonstrations that further improve zero-shot results.","url_abs":"https://arxiv.org/abs/2212.09865v2","url_pdf":"https://arxiv.org/pdf/2212.09865v2.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":"z-icl-zero-shot-in-context-learning-with","repo_url":"https://github.com/alrope123/z-icl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"z-icl-zero-shot-in-context-learning-with","repo_url":"https://github.com/social-ai-studio/pro-cap","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"in-context-learning","task_name":"In-Context Learning"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2212.09865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.09865"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/alrope123/z-icl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/social-ai-studio/pro-cap","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":1,"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":3,"samples":[{"code_sha256_prefix":"bc28b16c6293d681","entry":"get_source_corpus","repo":"alrope123/z-icl","repo_kind":"official","path":"scripts/retrieve.py","file_url":"https://github.com/alrope123/z-icl/blob/HEAD/scripts/retrieve.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"bc28b16c6293d681"}},{"code_sha256_prefix":"40e97f08f8dac82a","entry":"faiss_search","repo":"alrope123/z-icl","repo_kind":"official","path":"scripts/retrieve.py","file_url":"https://github.com/alrope123/z-icl/blob/HEAD/scripts/retrieve.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"40e97f08f8dac82a"}},{"code_sha256_prefix":"8e8bb6227bab7af4","entry":"run","repo":"alrope123/z-icl","repo_kind":"official","path":"scripts/run_inference.py","file_url":"https://github.com/alrope123/z-icl/blob/HEAD/scripts/run_inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"8e8bb6227bab7af4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}