Papers › MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference...

MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization

12 Jan 2024arXiv:2401.06838archive 2025-07-28

Shuaijie She, Wei Zou, ShuJian Huang, Wenhao Zhu, Xiang Liu, Xiang Geng, Jiajun Chen

Though reasoning abilities are considered language-agnostic, existing LLMs exhibit inconsistent reasoning abilities across different languages, e.g., reasoning in the dominant language like English is superior to other languages due to the imbalance of multilingual training data. To enhance reasoning abilities in non-dominant languages, we propose a Multilingual-Alignment-as-Preference Optimization framework (MAPO), aiming to align the reasoning processes in other languages with the dominant language. Specifically, we harness an off-the-shelf translation model for the consistency between answers in non-dominant and dominant languages, which we adopt as the preference for optimization, e.g., Direct Preference Optimization (DPO) or Proximal Policy Optimization (PPO). Experiments show that MAPO stably achieves significant improvements in the multilingual reasoning of various models on all three benchmarks (MSVAMP +16.2%, MGSM +6.1%, and MNumGLUESub +13.3%), with improved reasoning consistency across languages.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2401.06838")

Code

Syntology Ran 6 of 10 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 5 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

njunlp/mapo officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

10 samples harvested; 6 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
5ran
4unverified

Licence: 10 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from njunlp/mapo. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

check_repeated_sentences njunlp/mapo/Alignment/RM_Function.py official repository ran no licence file found · pointer only · f9d947865d5c2df5 · report
extract_last_num njunlp/mapo/Alignment/RM_Function.py official repository ran fingerprinted no licence file found · pointer only · 287846e257403143 · report
extract_prompt njunlp/mapo/Alignment/dpo.py official repository ran no licence file found · pointer only · e6cd16b73d39b2f9 · report
load_valuehead_params njunlp/mapo/Alignment/load_model.py official repository ran no licence file found · pointer only · 709e5380f7a98c0c · report
make_model_gradient_checkpointing_compatible njunlp/mapo/Alignment/rlhf_model.py official repository ran · our draft was wrong no licence file found · pointer only · 8a0c67573897efe9 · report
process njunlp/mapo/Preprocess/extract_dpo_data.py official repository ran fingerprinted no licence file found · pointer only · e72ea21ca5a7f293 · report
MultiLigual_Alighment_reward_fuction njunlp/mapo/Alignment/RM_Function.py official repository unverified no licence file found · pointer only · d2581bfd614214b2 · report
get_hh njunlp/mapo/Alignment/dpo.py official repository unverified no licence file found · pointer only · 6cb9adf1c32bb303 · report
get_hh njunlp/mapo/Alignment/dpo13B.py official repository unverified no licence file found · pointer only · 40ad288a296c417a · report
get_prompter njunlp/mapo/Alignment/generatePrompt.py official repository unverified no licence file found · pointer only · 870013f30ea56fa5 · report

Tasks

Mathematical Reasoning

Datasets

Introduced by this paper, per the archive.

MNumGLUESub

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGNEntropy RegularizationPPO

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections