{"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/pomp-probability-driven-meta-graph-prompter","title":"POMP: Probability-driven Meta-graph Prompter for LLMs in Low-resource Unsupervised Neural Machine Translation","arxiv_id":"2401.05596","date":"2024-01-11","proceeding":null,"authors":["Shilong Pan","Zhiliang Tian","Liang Ding","Zhen Huang","Zhihua Wen","Dongsheng Li"],"abstract":"Low-resource languages (LRLs) face challenges in supervised neural machine translation due to limited parallel data, prompting research into unsupervised methods. Unsupervised neural machine translation (UNMT) methods, including back-translation, transfer learning, and pivot-based translation, offer practical solutions for LRL translation, but they are hindered by issues like synthetic data noise, language bias, and error propagation, which can potentially be mitigated by Large Language Models (LLMs). LLMs have advanced NMT with in-context learning (ICL) and supervised fine-tuning methods, but insufficient training data results in poor performance in LRLs. We argue that LLMs can mitigate the linguistic noise with auxiliary languages to improve translations in LRLs. In this paper, we propose Probability-driven Meta-graph Prompter (POMP), a novel approach employing a dynamic, sampling-based graph of multiple auxiliary languages to enhance LLMs' translation capabilities for LRLs. POMP involves constructing a directed acyclic meta-graph for each source language, from which we dynamically sample multiple paths to prompt LLMs to mitigate the linguistic noise and improve translations during training. We use the BLEURT metric to evaluate the translations and back-propagate rewards, estimated by scores, to update the probabilities of auxiliary languages in the paths. Our experiments show significant improvements in the translation quality of three LRLs, demonstrating the effectiveness of our approach.","url_abs":"https://arxiv.org/abs/2401.05596v2","url_pdf":"https://arxiv.org/pdf/2401.05596v2.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":[],"tasks":[{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.05596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05596"}},"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/slpanir/POMP","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"ran_draft_wrong":1},"by_repo_kind":{"found_in_text":{"samples":4,"ran":4,"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":"fdb7bee668b7a80d","entry":"cal_similarity_wo_en","repo":"slpanir/POMP","repo_kind":"found_in_text","path":"encoder_outs.py","file_url":"https://github.com/slpanir/POMP/blob/HEAD/encoder_outs.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":"fdb7bee668b7a80d"}},{"code_sha256_prefix":"88ce019380f10478","entry":"get_symbols_to_strip_from_output","repo":"slpanir/POMP","repo_kind":"found_in_text","path":"encoder_outs.py","file_url":"https://github.com/slpanir/POMP/blob/HEAD/encoder_outs.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"88ce019380f10478"}},{"code_sha256_prefix":"82bdf940665aeeb4","entry":"safe_readline","repo":"slpanir/POMP","repo_kind":"found_in_text","path":"fairseq/binarizer.py","file_url":"https://github.com/slpanir/POMP/blob/HEAD/fairseq/binarizer.py","link_basis":"harvester_set","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":"82bdf940665aeeb4"}},{"code_sha256_prefix":"66bf918cbc1f0544","entry":"sample_from_file","repo":"slpanir/POMP","repo_kind":"found_in_text","path":"sample.py","file_url":"https://github.com/slpanir/POMP/blob/HEAD/sample.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":"66bf918cbc1f0544"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}