{"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/tower-an-open-multilingual-large-language","title":"Tower: An Open Multilingual Large Language Model for Translation-Related Tasks","arxiv_id":"2402.17733","date":"2024-02-27","proceeding":null,"authors":["Duarte M. Alves","José Pombal","Nuno M. Guerreiro","Pedro H. Martins","João Alves","Amin Farajian","Ben Peters","Ricardo Rei","Patrick Fernandes","Sweta Agrawal","Pierre Colombo","José G. C. de Souza","André F. T. Martins"],"abstract":"While general-purpose large language models (LLMs) demonstrate proficiency on multiple tasks within the domain of translation, approaches based on open LLMs are competitive only when specializing on a single task. In this paper, we propose a recipe for tailoring LLMs to multiple tasks present in translation workflows. We perform continued pretraining on a multilingual mixture of monolingual and parallel data, creating TowerBase, followed by finetuning on instructions relevant for translation processes, creating TowerInstruct. Our final model surpasses open alternatives on several tasks relevant to translation workflows and is competitive with general-purpose closed LLMs. To facilitate future research, we release the Tower models, our specialization dataset, an evaluation framework for LLMs focusing on the translation ecosystem, and a collection of model generations, including ours, on our benchmark.","url_abs":"https://arxiv.org/abs/2402.17733v1","url_pdf":"https://arxiv.org/pdf/2402.17733v1.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":"tower-an-open-multilingual-large-language","repo_url":"https://github.com/deep-spin/tower-eval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"tower-an-open-multilingual-large-language","repo_url":"https://github.com/epfllm/megatron-llm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"tower-an-open-multilingual-large-language","repo_url":"https://github.com/coldmist-lu/mqm_ape","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"tower-an-open-multilingual-large-language","repo_url":"https://github.com/dayeonki/rewrite_mt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.17733","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17733"}},"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/deep-spin/tower-eval","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/epfllm/megatron-llm","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dayeonki/rewrite_mt","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/coldmist-lu/mqm_ape","reach":{"status":"ok"}}],"summary":{"ran":7},"by_repo_kind":{"official":{"samples":7,"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":7,"samples":[{"code_sha256_prefix":"37646a69cb702ffb","entry":"args_to_dict","repo":"deep-spin/tower-eval","repo_kind":"official","path":"tower_eval/utils.py","file_url":"https://github.com/deep-spin/tower-eval/blob/HEAD/tower_eval/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"37646a69cb702ffb"}},{"code_sha256_prefix":"f1df9a32dfb79fcf","entry":"det_to_annotation","repo":"deep-spin/tower-eval","repo_kind":"official","path":"tower_eval/error_span_utils.py","file_url":"https://github.com/deep-spin/tower-eval/blob/HEAD/tower_eval/error_span_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f1df9a32dfb79fcf"}},{"code_sha256_prefix":"342c2ee4d566cd68","entry":"detokenize","repo":"deep-spin/tower-eval","repo_kind":"official","path":"tower_eval/utils.py","file_url":"https://github.com/deep-spin/tower-eval/blob/HEAD/tower_eval/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"342c2ee4d566cd68"}},{"code_sha256_prefix":"2e12a2f6139b0b1a","entry":"get_similar_examples","repo":"deep-spin/tower-eval","repo_kind":"official","path":"tower_eval/fewshot_retrieval_utils.py","file_url":"https://github.com/deep-spin/tower-eval/blob/HEAD/tower_eval/fewshot_retrieval_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2e12a2f6139b0b1a"}},{"code_sha256_prefix":"88595725d29c4865","entry":"ordered_retrieval","repo":"deep-spin/tower-eval","repo_kind":"official","path":"tower_eval/fewshot_retrieval_utils.py","file_url":"https://github.com/deep-spin/tower-eval/blob/HEAD/tower_eval/fewshot_retrieval_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"88595725d29c4865"}},{"code_sha256_prefix":"1e7fb93e26b69861","entry":"random_retrieval","repo":"deep-spin/tower-eval","repo_kind":"official","path":"tower_eval/fewshot_retrieval_utils.py","file_url":"https://github.com/deep-spin/tower-eval/blob/HEAD/tower_eval/fewshot_retrieval_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1e7fb93e26b69861"}},{"code_sha256_prefix":"91a71e23d5be4b27","entry":"tag_to_annotation","repo":"deep-spin/tower-eval","repo_kind":"official","path":"tower_eval/error_span_utils.py","file_url":"https://github.com/deep-spin/tower-eval/blob/HEAD/tower_eval/error_span_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"91a71e23d5be4b27"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}