{"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/self-augmented-in-context-learning-for","title":"Self-Augmented In-Context Learning for Unsupervised Word Translation","arxiv_id":"2402.10024","date":"2024-02-15","proceeding":null,"authors":["Yaoyiran Li","Anna Korhonen","Ivan Vulić"],"abstract":"Recent work has shown that, while large language models (LLMs) demonstrate strong word translation or bilingual lexicon induction (BLI) capabilities in few-shot setups, they still cannot match the performance of 'traditional' mapping-based approaches in the unsupervised scenario where no seed translation pairs are available, especially for lower-resource languages. To address this challenge with LLMs, we propose self-augmented in-context learning (SAIL) for unsupervised BLI: starting from a zero-shot prompt, SAIL iteratively induces a set of high-confidence word translation pairs for in-context learning (ICL) from an LLM, which it then reapplies to the same LLM in the ICL fashion. Our method shows substantial gains over zero-shot prompting of LLMs on two established BLI benchmarks spanning a wide range of language pairs, also outperforming mapping-based baselines across the board. In addition to achieving state-of-the-art unsupervised BLI performance, we also conduct comprehensive analyses on SAIL and discuss its limitations.","url_abs":"https://arxiv.org/abs/2402.10024v2","url_pdf":"https://arxiv.org/pdf/2402.10024v2.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":"self-augmented-in-context-learning-for","repo_url":"https://github.com/cambridgeltl/sail-bli","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"bilingual-lexicon-induction","task_name":"Bilingual Lexicon Induction"},{"task_slug":"cross-lingual-word-embeddings","task_name":"Cross-Lingual Word Embeddings"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"low-resource-neural-machine-translation","task_name":"Low-Resource Neural Machine Translation"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"multilingual-nlp","task_name":"Multilingual NLP"},{"task_slug":"prompt-engineering","task_name":"Prompt Engineering"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"word-alignment","task_name":"Word Alignment"},{"task_slug":"word-translation","task_name":"Word Translation"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.10024","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10024"}},"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":"deterministic:regex_extraction","url":"https://github.com/cambridgeltl/sail-bli","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7,"unverified":3},"by_repo_kind":{"official":{"samples":10,"ran":7,"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":"e76df3c849e328e1","entry":"apply_template","repo":"cambridgeltl/sail-bli","repo_kind":"official","path":"src/util.py","file_url":"https://github.com/cambridgeltl/sail-bli/blob/HEAD/src/util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e76df3c849e328e1"}},{"code_sha256_prefix":"c7ba302927a96f85","entry":"count_parameters","repo":"cambridgeltl/sail-bli","repo_kind":"official","path":"src/infer_seed_dic.py","file_url":"https://github.com/cambridgeltl/sail-bli/blob/HEAD/src/infer_seed_dic.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c7ba302927a96f85"}},{"code_sha256_prefix":"8664c08247da77bc","entry":"evaluate_bli","repo":"cambridgeltl/sail-bli","repo_kind":"official","path":"src/openaigen.py","file_url":"https://github.com/cambridgeltl/sail-bli/blob/HEAD/src/openaigen.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8664c08247da77bc"}},{"code_sha256_prefix":"4e758c201f0c3be2","entry":"get_best_template","repo":"cambridgeltl/sail-bli","repo_kind":"official","path":"src/util.py","file_url":"https://github.com/cambridgeltl/sail-bli/blob/HEAD/src/util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4e758c201f0c3be2"}},{"code_sha256_prefix":"2edd13eb7a270d11","entry":"get_templates","repo":"cambridgeltl/sail-bli","repo_kind":"official","path":"src/util.py","file_url":"https://github.com/cambridgeltl/sail-bli/blob/HEAD/src/util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2edd13eb7a270d11"}},{"code_sha256_prefix":"e5a4a12425cc40a8","entry":"my_sorted","repo":"cambridgeltl/sail-bli","repo_kind":"official","path":"src/extract_bli_test_data.py","file_url":"https://github.com/cambridgeltl/sail-bli/blob/HEAD/src/extract_bli_test_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e5a4a12425cc40a8"}},{"code_sha256_prefix":"01735bce9688a612","entry":"normed_input","repo":"cambridgeltl/sail-bli","repo_kind":"official","path":"src/extract_bli_test_data.py","file_url":"https://github.com/cambridgeltl/sail-bli/blob/HEAD/src/extract_bli_test_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"01735bce9688a612"}},{"code_sha256_prefix":"14544d1761941516","entry":"inference","repo":"cambridgeltl/sail-bli","repo_kind":"official","path":"src/infer_seed_dic.py","file_url":"https://github.com/cambridgeltl/sail-bli/blob/HEAD/src/infer_seed_dic.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":"14544d1761941516"}},{"code_sha256_prefix":"11030caebb5b7dcd","entry":"inference","repo":"cambridgeltl/sail-bli","repo_kind":"official","path":"src/openaigen.py","file_url":"https://github.com/cambridgeltl/sail-bli/blob/HEAD/src/openaigen.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":"11030caebb5b7dcd"}},{"code_sha256_prefix":"ce64f9a3237c454f","entry":"return_definition_wn","repo":"cambridgeltl/sail-bli","repo_kind":"official","path":"src/extract_bli_test_data.py","file_url":"https://github.com/cambridgeltl/sail-bli/blob/HEAD/src/extract_bli_test_data.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":"ce64f9a3237c454f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}