SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.13627 · 2023

InstructAlign: High-and-Low Resource Language Alignment via Continual Crosslingual Instruction Tuning

arXiv · PDF · Open in the Atlas

Code that ran

1 of 4 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 3 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/2305.13627.json · badge: /api/ran/2305.13627.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
hltchkust/instructalign canonical (classifier label)
classifier basis: classifier_2025
1 ran · 3 no recorded run
FunctionStatusWhere it lives
to_prompt Ran
ran; our contract draft was wrong, not the code
hltchkust/instructalign/main_nlu_prompt.py
code served (permissive licence) · get_code("d1e96734ec6f84dd")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Construct arguments for to_prompt function

# input: can be either dict with 'text' key or dict with 'text_1' and 'text_2' keys
input_single = {
    'text': 'This is the input text to process'
}

input_pair = {
    'text_1': 'First input text',
    'text_2': 'Second input text'
}

# prompt: string with placeholders like [INPUT], [INPUT_A], [INPUT_B], [OPTIONS]
prompt_single = 'Please classify the following: [INPUT]. Options: [OPTIONS]'
prompt_pair = 'Compare [INPUT_A] and [INPUT_B]. Which is better? [OPTIONS]'

# labels: list of label strings
labels_short = ['Yes', 'No']
labels_long = ['Option A', 'Option B', 'Option C']

# prompt_lang: string indicating language, checked for 'EN' substring
prompt_lang_en = 'EN'
prompt_lang_id = 'ID'

# Test case 1: single input with short labels
ARGS = {
    'input': input_single,
    'prompt': prompt_single,
    'labels': labels_short,
    'prompt_lang': prompt_lang_en
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_logprobs Not yet run
unverified (harvested, no recorded run)
hltchkust/instructalign/main_nlu_prompt.py
code served (permissive licence) · get_code("efd81d324c9b6a6f")
How it ran

no invocation recorded.

get_prompt Not yet run
unverified (harvested, no recorded run)
hltchkust/instructalign/nlu_prompt.py
code served (permissive licence) · get_code("9239c0977078e7fe")
How it ran

no invocation recorded.

predict_classification Not yet run
unverified (harvested, no recorded run)
hltchkust/instructalign/main_nlu_prompt.py
code served (permissive licence) · get_code("0e38ec2524e2b7d1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 3 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.

FunctionAlso present inEarliest-datedOthers named
predict_classification 1 other paper
1 later
2309.10661 (2023-09)
NusaWrites: Constructing High-Quality Corpora for Underrepresented and Extremely Low-Resource Languages

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 (LLMs) that are tuned with instructions have demonstrated remarkable capabilities in various tasks and languages. However, their ability to generalize to underrepresented languages is limited due to the scarcity of available data. Additionally, directly adapting new languages to instruction-tuned LLMs can result in catastrophic forgetting, which leads to the loss of multitasking ability. To address this issue, we propose InstructAlign which uses continual crosslingual instruction tuning to enable LLMs to align new unseen languages with previously learned high-resource languages. Our results demonstrate the effectiveness of InstructAlign in enabling the model to understand low-resource languages with limited parallel data while preventing catastrophic forgetting. Our work contributes to the advancement of language adaptation methods, particularly for adapting instruction-tuned LLMs to underrepresented languages. Our code is released on https://github.com/HLTCHKUST/InstructAlign

For agents

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

get_harvested_code_for_paper("2305.13627")
get_code_for_paper("2305.13627")
have("2305.13627")

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

curl https://syntology.ai/api/ran/2305.13627.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.13627.svg)](https://syntology.ai/paper/2305.13627)

Connect an agent — have() is free.