{"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/proxylm-predicting-language-model-performance","title":"ProxyLM: Predicting Language Model Performance on Multilingual Tasks via Proxy Models","arxiv_id":"2406.09334","date":"2024-06-13","proceeding":null,"authors":["David Anugraha","Genta Indra Winata","Chenyue Li","Patrick Amadeus Irawan","En-Shiun Annie Lee"],"abstract":"Performance prediction is a method to estimate the performance of Language Models (LMs) on various Natural Language Processing (NLP) tasks, mitigating computational costs associated with model capacity and data for fine-tuning. Our paper presents ProxyLM, a scalable task- and language-agnostic framework designed to predict the performance of LMs using proxy models. These proxy models act as surrogates, approximating the performance of the LM of interest. By leveraging these proxy models, ProxyLM significantly reduces computational overhead in task evaluations, achieving up to a 37.08x speedup over traditional methods, even with our smallest proxy models. Our results across multiple multilingual NLP tasks and various robustness tests demonstrate that ProxyLM not only adapts well to previously unseen languages in pre-trained LMs, but also generalizes effectively across different datasets, outperforming the state-of-the-art by at least 1.78x in terms of root-mean-square error (RMSE).","url_abs":"https://arxiv.org/abs/2406.09334v3","url_pdf":"https://arxiv.org/pdf/2406.09334v3.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":"proxylm-predicting-language-model-performance","repo_url":"https://github.com/davidanugraha/proxylm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"model-selection","task_name":"Model Selection"},{"task_slug":"multilingual-nlp","task_name":"Multilingual NLP"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.09334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09334"}},"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/davidanugraha/proxylm","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"unverified":4},"by_repo_kind":{"official":{"samples":7,"ran":3,"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":"8cd398e34d47a59e","entry":"add_comet_score_stats_to_entry","repo":"davidanugraha/proxylm","repo_kind":"official","path":"src/utils/convert_experiments_to_csv.py","file_url":"https://github.com/davidanugraha/proxylm/blob/HEAD/src/utils/convert_experiments_to_csv.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8cd398e34d47a59e"}},{"code_sha256_prefix":"81a289db46224607","entry":"add_comet_score_stats_to_entry","repo":"davidanugraha/proxylm","repo_kind":"official","path":"src/utils/convert_experiments_to_csv_by_lang.py","file_url":"https://github.com/davidanugraha/proxylm/blob/HEAD/src/utils/convert_experiments_to_csv_by_lang.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"81a289db46224607"}},{"code_sha256_prefix":"5e9b8a2d6b803f65","entry":"calculate_jsd","repo":"davidanugraha/proxylm","repo_kind":"official","path":"src/utils/dataset_featurization.py","file_url":"https://github.com/davidanugraha/proxylm/blob/HEAD/src/utils/dataset_featurization.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5e9b8a2d6b803f65"}},{"code_sha256_prefix":"3b1e36adeaca8622","entry":"get_test_outputs","repo":"davidanugraha/proxylm","repo_kind":"official","path":"src/utils/convert_experiments_to_csv.py","file_url":"https://github.com/davidanugraha/proxylm/blob/HEAD/src/utils/convert_experiments_to_csv.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3b1e36adeaca8622"}},{"code_sha256_prefix":"6eecb17affc53102","entry":"get_test_outputs","repo":"davidanugraha/proxylm","repo_kind":"official","path":"src/utils/convert_experiments_to_csv_by_lang.py","file_url":"https://github.com/davidanugraha/proxylm/blob/HEAD/src/utils/convert_experiments_to_csv_by_lang.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6eecb17affc53102"}},{"code_sha256_prefix":"ea7af90f494d8472","entry":"parse_txt_file","repo":"davidanugraha/proxylm","repo_kind":"official","path":"src/utils/convert_experiments_to_csv.py","file_url":"https://github.com/davidanugraha/proxylm/blob/HEAD/src/utils/convert_experiments_to_csv.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ea7af90f494d8472"}},{"code_sha256_prefix":"e24612156d65a2e5","entry":"parse_txt_file","repo":"davidanugraha/proxylm","repo_kind":"official","path":"src/utils/convert_experiments_to_csv_by_lang.py","file_url":"https://github.com/davidanugraha/proxylm/blob/HEAD/src/utils/convert_experiments_to_csv_by_lang.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e24612156d65a2e5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}