{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/language-imbalance-driven-rewarding-for","title":"Language Imbalance Driven Rewarding for Multilingual Self-improving","arxiv_id":"2410.08964","date":"2024-10-11","proceeding":null,"authors":["Wen Yang","Junhong Wu","Chen Wang","Chengqing Zong","Jiajun Zhang"],"abstract":"Large Language Models (LLMs) have achieved state-of-the-art performance across numerous tasks. However, these advancements have predominantly benefited \"first-class\" languages such as English and Chinese, leaving many other languages underrepresented. This imbalance, while limiting broader applications, generates a natural preference ranking between languages, offering an opportunity to bootstrap the multilingual capabilities of LLM in a self-improving manner. Thus, we propose $\\textit{Language Imbalance Driven Rewarding}$, where the inherent imbalance between dominant and non-dominant languages within LLMs is leveraged as a reward signal. Iterative DPO training demonstrates that this approach not only enhances LLM performance in non-dominant languages but also improves the dominant language's capacity, thereby yielding an iterative reward signal. Fine-tuning Meta-Llama-3-8B-Instruct over two iterations of this approach results in continuous improvements in multilingual performance across instruction-following and arithmetic reasoning tasks, evidenced by an average improvement of 7.46% win rate on the X-AlpacaEval leaderboard and 13.9% accuracy on the MGSM benchmark. This work serves as an initial exploration, paving the way for multilingual self-improvement of LLMs.","url_abs":"https://arxiv.org/abs/2410.08964v2","url_pdf":"https://arxiv.org/pdf/2410.08964v2.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":"language-imbalance-driven-rewarding-for","repo_url":"https://github.com/znlp/language-imbalance-driven-rewarding","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"arithmetic-reasoning","task_name":"Arithmetic Reasoning"},{"task_slug":"instruction-following","task_name":"Instruction Following"}],"methods":[{"method_slug":"dpo","method_name":"DPO"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.08964","atlas_url":"https://app.syntology.ai/?focus=2410.08964","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08964"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.08964"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.08964"},"call":"get_harvested_code_for_paper(arxiv_id=\"2410.08964\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2410.08964"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2410.08964\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2410.08964"},"call":"get_concepts_for_paper(arxiv_id=\"2410.08964\")"}],"by_repo":[{"repo":"znlp/language-imbalance-driven-rewarding","kind":"official","samples":13,"ran":8,"instrument":6,"unverified":5}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2410.08964.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2410.08964.svg"},"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/ZNLP/Language-Imbalance-Driven-Rewarding","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/znlp/language-imbalance-driven-rewarding","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":6,"ran_honours":2,"unverified":5},"n_samples":13,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":5,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":13,"ran":8,"n_ran_checked":2,"n_instrument":6,"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":13,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":7,"n_ran_without_level_date":1,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"c85bc1200cde30f4","code_sha256_prefix":"c85bc1200cde30f4","entry":"generator","repo":"znlp/language-imbalance-driven-rewarding","repo_kind":"official","path":"utils/batch_inference.py","file_url":"https://github.com/znlp/language-imbalance-driven-rewarding/blob/HEAD/utils/batch_inference.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,"signature":"solver:MockSolver/0/?, output:str/0/str","fixture_out_type":"MockSolver","code_page":"/code/generator-2","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, znlp/language-imbalance-driven-rewarding when it was checked","mcp_get_code":{"code_sha256":"c85bc1200cde30f4"}},{"code_sha256":"11e86e115ad397d4","code_sha256_prefix":"11e86e115ad397d4","entry":"get_file_names","repo":"ZNLP/Language-Imbalance-Driven-Rewarding","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/ZNLP/Language-Imbalance-Driven-Rewarding/blob/HEAD/utils/utils.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,"signature":"dir_path:str/0/str","fixture_out_type":"list","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/get-file-names","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ZNLP/Language-Imbalance-Driven-Rewarding when it was checked","mcp_get_code":{"code_sha256":"11e86e115ad397d4"}},{"code_sha256":"0c77763ca4cd8bc4","code_sha256_prefix":"0c77763ca4cd8bc4","entry":"get_metrics_evaluator","repo":"ZNLP/Language-Imbalance-Driven-Rewarding","repo_kind":"official","path":"alpaca_eval/src/alpaca_eval/analyze.py","file_url":"https://github.com/ZNLP/Language-Imbalance-Driven-Rewarding/blob/HEAD/alpaca_eval/src/alpaca_eval/analyze.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"analyzer:MockAnalyzer/0/?, df_crossannotations:DataFrame/0/?, evaluator_name:str/0/str","fixture_out_type":"dict","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/get-metrics-evaluator","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ZNLP/Language-Imbalance-Driven-Rewarding when it was checked","mcp_get_code":{"code_sha256":"0c77763ca4cd8bc4"}},{"code_sha256":"80319fda62fe1a04","code_sha256_prefix":"80319fda62fe1a04","entry":"lmsys_parser","repo":"ZNLP/Language-Imbalance-Driven-Rewarding","repo_kind":"official","path":"alpaca_eval/src/alpaca_eval/completion_parsers.py","file_url":"https://github.com/ZNLP/Language-Imbalance-Driven-Rewarding/blob/HEAD/alpaca_eval/src/alpaca_eval/completion_parsers.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"completion:str/0/str","fixture_out_type":"list","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"80319fda62fe1a04"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ZNLP/Language-Imbalance-Driven-Rewarding when it was checked","mcp_get_code":{"code_sha256":"80319fda62fe1a04"}},{"code_sha256":"10b24db4baa49194","code_sha256_prefix":"10b24db4baa49194","entry":"load_json","repo":"ZNLP/Language-Imbalance-Driven-Rewarding","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/ZNLP/Language-Imbalance-Driven-Rewarding/blob/HEAD/utils/utils.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,"signature":"file_path:str/0/str","fixture_out_type":"dict","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/load-json","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ZNLP/Language-Imbalance-Driven-Rewarding when it was checked","mcp_get_code":{"code_sha256":"10b24db4baa49194"}},{"code_sha256":"4ccfe92e7eff858a","code_sha256_prefix":"4ccfe92e7eff858a","entry":"load_jsonl","repo":"ZNLP/Language-Imbalance-Driven-Rewarding","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/ZNLP/Language-Imbalance-Driven-Rewarding/blob/HEAD/utils/utils.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,"signature":"file_path:str/0/str","fixture_out_type":"list","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/load-jsonl","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ZNLP/Language-Imbalance-Driven-Rewarding when it was checked","mcp_get_code":{"code_sha256":"4ccfe92e7eff858a"}},{"code_sha256":"52f4a49b6393e97e","code_sha256_prefix":"52f4a49b6393e97e","entry":"ranking_parser","repo":"ZNLP/Language-Imbalance-Driven-Rewarding","repo_kind":"official","path":"alpaca_eval/src/alpaca_eval/completion_parsers.py","file_url":"https://github.com/ZNLP/Language-Imbalance-Driven-Rewarding/blob/HEAD/alpaca_eval/src/alpaca_eval/completion_parsers.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"completion:str/0/str, model_1_name:str/0/str","fixture_out_type":"list","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ZNLP/Language-Imbalance-Driven-Rewarding when it was checked","mcp_get_code":{"code_sha256":"52f4a49b6393e97e"}},{"code_sha256":"307648f4b5ffd08b","code_sha256_prefix":"307648f4b5ffd08b","entry":"show_length_gameability","repo":"ZNLP/Language-Imbalance-Driven-Rewarding","repo_kind":"official","path":"alpaca_eval/src/alpaca_eval/plotting.py","file_url":"https://github.com/ZNLP/Language-Imbalance-Driven-Rewarding/blob/HEAD/alpaca_eval/src/alpaca_eval/plotting.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"df:DataFrame/0/?","fixture_out_type":"Styler","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ZNLP/Language-Imbalance-Driven-Rewarding when it was checked","mcp_get_code":{"code_sha256":"307648f4b5ffd08b"}},{"code_sha256":"304d6b64de10aa4f","code_sha256_prefix":"304d6b64de10aa4f","entry":"get_alpaca_eval_data","repo":"ZNLP/Language-Imbalance-Driven-Rewarding","repo_kind":"official","path":"alpaca_eval/src/alpaca_eval/constants.py","file_url":"https://github.com/ZNLP/Language-Imbalance-Driven-Rewarding/blob/HEAD/alpaca_eval/src/alpaca_eval/constants.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ZNLP/Language-Imbalance-Driven-Rewarding when it was checked","mcp_get_code":{"code_sha256":"304d6b64de10aa4f"}},{"code_sha256":"0eb53db38f0faafd","code_sha256_prefix":"0eb53db38f0faafd","entry":"get_annotations","repo":"ZNLP/Language-Imbalance-Driven-Rewarding","repo_kind":"official","path":"alpaca_eval/src/alpaca_eval/analyze.py","file_url":"https://github.com/ZNLP/Language-Imbalance-Driven-Rewarding/blob/HEAD/alpaca_eval/src/alpaca_eval/analyze.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/get-annotations","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ZNLP/Language-Imbalance-Driven-Rewarding when it was checked","mcp_get_code":{"code_sha256":"0eb53db38f0faafd"}},{"code_sha256":"de8a267bb7f7d4bd","code_sha256_prefix":"de8a267bb7f7d4bd","entry":"get_crossannotations","repo":"ZNLP/Language-Imbalance-Driven-Rewarding","repo_kind":"official","path":"alpaca_eval/src/alpaca_eval/analyze.py","file_url":"https://github.com/ZNLP/Language-Imbalance-Driven-Rewarding/blob/HEAD/alpaca_eval/src/alpaca_eval/analyze.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/get-crossannotations","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ZNLP/Language-Imbalance-Driven-Rewarding when it was checked","mcp_get_code":{"code_sha256":"de8a267bb7f7d4bd"}},{"code_sha256":"be8e5acf8fee5a8f","code_sha256_prefix":"be8e5acf8fee5a8f","entry":"plot_heatmap_diff_baseline","repo":"ZNLP/Language-Imbalance-Driven-Rewarding","repo_kind":"official","path":"alpaca_eval/src/alpaca_eval/plotting.py","file_url":"https://github.com/ZNLP/Language-Imbalance-Driven-Rewarding/blob/HEAD/alpaca_eval/src/alpaca_eval/plotting.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ZNLP/Language-Imbalance-Driven-Rewarding when it was checked","mcp_get_code":{"code_sha256":"be8e5acf8fee5a8f"}},{"code_sha256":"6f7ea5efc95b3173","code_sha256_prefix":"6f7ea5efc95b3173","entry":"regex_parser","repo":"ZNLP/Language-Imbalance-Driven-Rewarding","repo_kind":"official","path":"alpaca_eval/src/alpaca_eval/completion_parsers.py","file_url":"https://github.com/ZNLP/Language-Imbalance-Driven-Rewarding/blob/HEAD/alpaca_eval/src/alpaca_eval/completion_parsers.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ZNLP/Language-Imbalance-Driven-Rewarding when it was checked","mcp_get_code":{"code_sha256":"6f7ea5efc95b3173"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"76c20df496537b6254ef01c57a12c7fa7d714d40df15756c1516930323c5d013","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}