Papers › Self-Augmented In-Context Learning for Unsupervised Word Translation

Self-Augmented In-Context Learning for Unsupervised Word Translation

15 Feb 2024arXiv:2402.10024archive 2025-07-28

Yaoyiran Li, Anna Korhonen, Ivan Vulić

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.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2402.10024")

Code

Syntology Ran 7 of 10 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 7 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

cambridgeltl/sail-bli officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

10 samples harvested; 7 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

7ran
3unverified

Licence: 0 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from cambridgeltl/sail-bli. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

apply_template cambridgeltl/sail-bli/src/util.py official repository ran MIT (permissive) · e76df3c849e328e1 · report
count_parameters cambridgeltl/sail-bli/src/infer_seed_dic.py official repository ran MIT (permissive) · c7ba302927a96f85 · report
evaluate_bli cambridgeltl/sail-bli/src/openaigen.py official repository ran MIT (permissive) · 8664c08247da77bc · report
get_best_template cambridgeltl/sail-bli/src/util.py official repository ran MIT (permissive) · 4e758c201f0c3be2 · report
get_templates cambridgeltl/sail-bli/src/util.py official repository ran MIT (permissive) · 2edd13eb7a270d11 · report
my_sorted cambridgeltl/sail-bli/src/extract_bli_test_data.py official repository ran MIT (permissive) · e5a4a12425cc40a8 · report
normed_input cambridgeltl/sail-bli/src/extract_bli_test_data.py official repository ran fingerprinted MIT (permissive) · 01735bce9688a612 · report
inference cambridgeltl/sail-bli/src/infer_seed_dic.py official repository unverified MIT (permissive) · 14544d1761941516 · report
inference cambridgeltl/sail-bli/src/openaigen.py official repository unverified MIT (permissive) · 11030caebb5b7dcd · report
return_definition_wn cambridgeltl/sail-bli/src/extract_bli_test_data.py official repository unverified MIT (permissive) · ce64f9a3237c454f · report

Tasks

Bilingual Lexicon InductionCross-Lingual Word EmbeddingsFew-Shot LearningIn-Context LearningLarge Language ModelLow-Resource Neural Machine TranslationMachine TranslationMultilingual NLPPrompt EngineeringTranslationWord AlignmentWord Translation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections