{"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/in-context-examples-selection-for-machine","title":"In-context Examples Selection for Machine Translation","arxiv_id":"2212.02437","date":"2022-12-05","proceeding":null,"authors":["Sweta Agrawal","Chunting Zhou","Mike Lewis","Luke Zettlemoyer","Marjan Ghazvininejad"],"abstract":"Large-scale generative models show an impressive ability to perform a wide range of Natural Language Processing (NLP) tasks using in-context learning, where a few examples are used to describe a task to the model. For Machine Translation (MT), these examples are typically randomly sampled from the development dataset with a similar distribution as the evaluation set. However, it is unclear how the choice of these in-context examples and their ordering impacts the output translation quality. In this work, we aim to understand the properties of good in-context examples for MT in both in-domain and out-of-domain settings. We show that the translation quality and the domain of the in-context examples matter and that 1-shot noisy unrelated example can have a catastrophic impact on output quality. While concatenating multiple random examples reduces the effect of noise, a single good prompt optimized to maximize translation quality on the development dataset can elicit learned information from the pre-trained language model. Adding similar examples based on an n-gram overlap with the test source significantly and consistently improves the translation quality of the outputs, outperforming a strong kNN-MT baseline in 2 out of 4 out-of-domain datasets.","url_abs":"https://arxiv.org/abs/2212.02437v1","url_pdf":"https://arxiv.org/pdf/2212.02437v1.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":"in-context-examples-selection-for-machine","repo_url":"https://github.com/armelrandy/icl-mt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"in-context-examples-selection-for-machine","repo_url":"https://github.com/sweta20/incontextmt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2212.02437","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.02437"}},"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/armelrandy/icl-mt","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sweta20/incontextmt","reach":null}],"summary":{"ran_draft_wrong":2,"unverified":7},"by_repo_kind":{"listed":{"samples":9,"ran":2,"repositories":2}},"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":2,"samples":[{"code_sha256_prefix":"9213942ca8c46cb3","entry":"get_outputs","repo":"sweta20/incontextmt","repo_kind":"listed","path":"run_metrics_eval.py","file_url":"https://github.com/sweta20/incontextmt/blob/HEAD/run_metrics_eval.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9213942ca8c46cb3"}},{"code_sha256_prefix":"c211341220630f0a","entry":"read_file","repo":"sweta20/incontextmt","repo_kind":"listed","path":"run_metrics_eval.py","file_url":"https://github.com/sweta20/incontextmt/blob/HEAD/run_metrics_eval.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c211341220630f0a"}},{"code_sha256_prefix":"4c1e8ffec89c5351","entry":"average_pool","repo":"armelrandy/icl-mt","repo_kind":"listed","path":"miscellaneous/embedding.py","file_url":"https://github.com/armelrandy/icl-mt/blob/HEAD/miscellaneous/embedding.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4c1e8ffec89c5351"}},{"code_sha256_prefix":"81e0cf4e48cd09c5","entry":"get_ngram_overlap_count","repo":"armelrandy/icl-mt","repo_kind":"listed","path":"create_recall_set_selection.py","file_url":"https://github.com/armelrandy/icl-mt/blob/HEAD/create_recall_set_selection.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"81e0cf4e48cd09c5"}},{"code_sha256_prefix":"60c3fa0b38fe859d","entry":"get_recall_overlap_score","repo":"armelrandy/icl-mt","repo_kind":"listed","path":"create_recall_set_selection.py","file_url":"https://github.com/armelrandy/icl-mt/blob/HEAD/create_recall_set_selection.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"60c3fa0b38fe859d"}},{"code_sha256_prefix":"5c0c0ea656370837","entry":"get_template","repo":"armelrandy/icl-mt","repo_kind":"listed","path":"templates.py","file_url":"https://github.com/armelrandy/icl-mt/blob/HEAD/templates.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5c0c0ea656370837"}},{"code_sha256_prefix":"2e5899bbe725001b","entry":"hf_generate","repo":"armelrandy/icl-mt","repo_kind":"listed","path":"inference.py","file_url":"https://github.com/armelrandy/icl-mt/blob/HEAD/inference.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2e5899bbe725001b"}},{"code_sha256_prefix":"e4996a7942440bb5","entry":"my_log","repo":"armelrandy/icl-mt","repo_kind":"listed","path":"create_recall_set_selection.py","file_url":"https://github.com/armelrandy/icl-mt/blob/HEAD/create_recall_set_selection.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e4996a7942440bb5"}},{"code_sha256_prefix":"88bb170e90013b2a","entry":"remove_emojis","repo":"armelrandy/icl-mt","repo_kind":"listed","path":"histogram.py","file_url":"https://github.com/armelrandy/icl-mt/blob/HEAD/histogram.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"88bb170e90013b2a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}