SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.16222 · EMNLP · 2024

PREALIGN: Boosting Cross-Lingual Transfer by Early Establishment of Multilingual Alignment

Shujian Huang, Jiajun Chen, Xinyu Dai, Jiahuan Li

arXiv · PDF · Open in the Atlas

Code that ran

4 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 5 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2407.16222.json · badge: /api/ran/2407.16222.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
saltychtao/prealign canonical (classifier label)
classifier basis: census
4 ran · 5 no recorded run
FunctionStatusWhere it lives
get_model Ran
ran; our contract draft was wrong, not the code
saltychtao/prealign/src/bilingual_dictionary_pretrain.py
pointer only (licence: NONE) · get_code("7f364484fd8d9cd5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, saltychtao/prealign when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

make_peft_config Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
saltychtao/prealign/src/utils.py
pointer only (licence: NONE) · get_code("6ec7b3cab391e5be")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, saltychtao/prealign when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_layers Ran
ran, honoured the contract we drafted
saltychtao/prealign/src/trainer/trainer_utils.py
pointer only (licence: NONE) · get_code("de478a94ef58d2c2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, saltychtao/prealign when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

solve_relaxed_wmd Ran
ran; our contract draft was wrong, not the code
saltychtao/prealign/src/trainer/trainer_utils.py
pointer only (licence: NONE) · get_code("1f742ae7e8dc30dd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, saltychtao/prealign when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

build_metric Not yet run
unverified (harvested, no recorded run)
saltychtao/prealign/src/trainer/trainer_utils.py
pointer only (licence: NONE) · get_code("dded2984b242fce8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, saltychtao/prealign when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

generate Not yet run
unverified (harvested, no recorded run)
saltychtao/prealign/src/utils.py
pointer only (licence: NONE) · get_code("17dae1edb93fa6da")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, saltychtao/prealign when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_model Not yet run
unverified (harvested, no recorded run)
saltychtao/prealign/src/multilingual_alignment.py
pointer only (licence: NONE) · get_code("6f97439faf35293d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, saltychtao/prealign when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_model Not yet run
unverified (harvested, no recorded run)
saltychtao/prealign/src/pretrain.py
pointer only (licence: NONE) · get_code("786ffbeb38364699")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, saltychtao/prealign when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

load_model_and_tokenizer Not yet run
unverified (harvested, no recorded run)
saltychtao/prealign/src/utils.py
pointer only (licence: NONE) · get_code("c6ea57e16ccfac13")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, saltychtao/prealign when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 9 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large language models demonstrate reasonable multilingual abilities, despite predominantly English-centric pretraining. However, the spontaneous multilingual alignment in these models is shown to be weak, leading to unsatisfactory cross-lingual transfer and knowledge sharing. Previous works attempt to address this issue by explicitly injecting multilingual alignment information during or after pretraining. Thus for the early stage in pretraining, the alignment is weak for sharing information or knowledge across languages. In this paper, we propose PREALIGN, a framework that establishes multilingual alignment prior to language model pretraining. PREALIGN injects multilingual alignment by initializing the model to generate similar representations of aligned words and preserves this alignment using a code-switching strategy during pretraining. Extensive experiments in a synthetic English to English-Clone setting demonstrate that PREALIGN significantly outperforms standard multilingual joint training in language modeling, zero-shot crosslingual transfer, and cross-lingual knowledge application. Further experiments in real-world scenarios further validate PREALIGN's effectiveness across various languages and model sizes. 1

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2407.16222")
get_code_for_paper("2407.16222")
have("2407.16222")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2407.16222.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2407.16222.svg)](https://syntology.ai/paper/2407.16222)

Connect an agent — have() is free.