{"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/ladder-a-model-agnostic-framework-boosting","title":"Ladder: A Model-Agnostic Framework Boosting LLM-based Machine Translation to the Next Level","arxiv_id":"2406.15741","date":"2024-06-22","proceeding":null,"authors":["Zhaopeng Feng","Ruizhe Chen","Yan Zhang","Zijie Meng","Zuozhu Liu"],"abstract":"General-purpose Large Language Models (LLMs) like GPT-4 have achieved remarkable advancements in machine translation (MT) by leveraging extensive web content. On the other hand, translation-specific LLMs are built by pre-training on domain-specific monolingual corpora and fine-tuning with human-annotated translation data. Despite the superior performance, these methods either demand an unprecedented scale of computing and data or substantial human editing and annotation efforts. In this paper, we develop MT-Ladder, a novel model-agnostic and cost-effective tool to refine the performance of general LLMs for MT. MT-Ladder is trained on pseudo-refinement triplets which can be easily obtained from existing LLMs without additional human cost. During training, we propose a hierarchical fine-tuning strategy with an easy-to-hard schema, improving MT-Ladder's refining performance progressively. The trained MT-Ladder can be seamlessly integrated with any general-purpose LLMs to boost their translation performance. By utilizing Gemma-2B/7B as the backbone, MT-Ladder-2B can elevate raw translations to the level of top-tier open-source models (e.g., refining BigTranslate-13B with +6.91 BLEU and +3.52 COMET for XX-En), and MT-Ladder-7B can further enhance model performance to be on par with the state-of-the-art GPT-4. Extensive ablation and analysis corroborate the effectiveness of MT-Ladder in diverse settings. Our code is available at https://github.com/fzp0424/MT-Ladder","url_abs":"https://arxiv.org/abs/2406.15741v3","url_pdf":"https://arxiv.org/pdf/2406.15741v3.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":"ladder-a-model-agnostic-framework-boosting","repo_url":"https://github.com/fzp0424/ladder","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"ladder-a-model-agnostic-framework-boosting","repo_url":"https://github.com/fzp0424/mt-ladder","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"ladder-a-model-agnostic-framework-boosting","repo_url":"https://github.com/fzp0424/self_correct_mt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.15741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.15741"}},"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/fzp0424/mt-ladder","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fzp0424/self_correct_mt","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fzp0424/ladder","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/fzp0424/MT-Ladder","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2,"unverified":6},"by_repo_kind":{"official":{"samples":8,"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":8,"samples":[{"code_sha256_prefix":"ffed8fe7e136c36b","entry":"get_inter_prompt","repo":"fzp0424/MT-Ladder","repo_kind":"official","path":"utils/build_dataset.py","file_url":"https://github.com/fzp0424/MT-Ladder/blob/HEAD/utils/build_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ffed8fe7e136c36b"}},{"code_sha256_prefix":"5f991a85de07720c","entry":"get_plain_prompt","repo":"fzp0424/MT-Ladder","repo_kind":"official","path":"utils/build_dataset.py","file_url":"https://github.com/fzp0424/MT-Ladder/blob/HEAD/utils/build_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5f991a85de07720c"}},{"code_sha256_prefix":"bdd9da0b8a3cb233","entry":"build_instruction_dataset","repo":"fzp0424/MT-Ladder","repo_kind":"official","path":"utils/build_dataset.py","file_url":"https://github.com/fzp0424/MT-Ladder/blob/HEAD/utils/build_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bdd9da0b8a3cb233"}},{"code_sha256_prefix":"43c9b0db7cb0dbf8","entry":"build_instruction_dataset","repo":"fzp0424/ladder","repo_kind":"official","path":"utils/build_dataset.py","file_url":"https://github.com/fzp0424/ladder/blob/HEAD/utils/build_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"43c9b0db7cb0dbf8"}},{"code_sha256_prefix":"efe50e9a77cff229","entry":"extract_fields","repo":"fzp0424/MT-Ladder","repo_kind":"official","path":"utils/build_dataset.py","file_url":"https://github.com/fzp0424/MT-Ladder/blob/HEAD/utils/build_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"efe50e9a77cff229"}},{"code_sha256_prefix":"fdc695f363873b0f","entry":"get_inter_prompt","repo":"fzp0424/ladder","repo_kind":"official","path":"utils/build_dataset.py","file_url":"https://github.com/fzp0424/ladder/blob/HEAD/utils/build_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fdc695f363873b0f"}},{"code_sha256_prefix":"0de43ceaf0a0a901","entry":"get_plain_prompt","repo":"fzp0424/ladder","repo_kind":"official","path":"utils/build_dataset.py","file_url":"https://github.com/fzp0424/ladder/blob/HEAD/utils/build_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0de43ceaf0a0a901"}},{"code_sha256_prefix":"e5ddc52f235c901e","entry":"load_pair_dataset","repo":"fzp0424/ladder","repo_kind":"official","path":"inference.py","file_url":"https://github.com/fzp0424/ladder/blob/HEAD/inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e5ddc52f235c901e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}