SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.01922 · 2023

Resources and Few-shot Learners for In-context Learning in Slavic Languages

arXiv · PDF · Open in the Atlas

Code that ran

2 of 5 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 2 have no contract verdict; 0 failures 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/2304.01922.json · badge: /api/ran/2304.01922.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
fewshot-goes-multilingual/slavic-incontext-learning canonical (classifier label)
classifier basis not recorded on the link
2 ran · 3 no recorded run
FunctionStatusWhere it lives
get_dataset_by_task_id Ran
ran on a synthesized input
fewshot-goes-multilingual/slavic-incontext-learning/evaluation/tasks/multilingual_datasets_index.py
code served (permissive licence) · get_code("8d61e6fa9743bd5b")
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, through the batch API) and returned Dataset. 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.

from datasets import Dataset

# Create mock datasets for each language/task combination
mock_dataset = Dataset.from_dict({
    "text": ["sample text 1", "sample text 2"],
    "label": [0, 1]
})

# Mock the customized_datasets modules for each language
import sys
from types import ModuleType

def create_mock_customized_datasets():
    """Create a mock module with get_all_datasets function"""
    mock_module = ModuleType("customized_datasets")
    
    def get_all_datasets(training_split=False):
        return {
            "task_1": mock_dataset,
            "task_2": mock_dataset,
            "task_3": mock_dataset,
        }
    
    mock_module.get_all_datasets = get_all_datasets
    return mock_module

# Create mock evaluation.tasks submodules
evaluation_module = ModuleType("evaluation")
tasks_module = ModuleType("tasks")
cs_module = ModuleType("cs")
ru_module = ModuleType("ru")
pl_module = ModuleType("pl")

cs_module.customized_datasets = create_mock_customized_datasets()
ru_module.customized_datasets = create_mock_customized_datasets()
pl_module.customized_datasets = create_mock_customized_datasets()

cs_module.__dict__["customized_datasets"] = cs_module.customized_datasets
ru_module.__dict__["customized_datasets"] = ru_module.customized_datasets
pl_module.__dict__["customized_datasets"] = pl_module.customized_datasets

tasks_module.cs = cs_module
tasks_module.ru = ru_module
tasks_module.pl = pl_module

evaluation_module.tasks = tasks_module

sys.modules["evaluation"] = evaluation_module
sys.modules["evaluation.tasks"] = tasks_module
sys.modules["evaluation.tasks.cs"] = cs_module
sys.modules["evaluation.tasks.cs.customized_datasets"] = cs_module.customized_datasets
sys.modules["evaluation.tasks.ru"] = ru_module
sys.modules["evaluation.tasks.ru.customized_datasets"] = ru_module.customized_datasets
sys.modules["evaluation.tasks.pl"] = pl_module
sys.modules["evaluation.tasks.pl.customized_datasets"] = pl_module.customized_datasets

ARGS = {
    "task_id": "task_1",
    "lang_id": "cs",
    "training_split": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
datasets, evaluation — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Dataset — a Dataset output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Dataset output the recorded ndim 1 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_datasets_by_lang Ran
ran on a synthesized input
fewshot-goes-multilingual/slavic-incontext-learning/evaluation/tasks/multilingual_datasets_index.py
code served (permissive licence) · get_code("6a27d36eedccd726")
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, through the batch API) and returned dict. 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
from datasets import Dataset
from typing import Dict

# The function takes a language ID and a training_split boolean flag
# It returns a Dict[str, Dataset]
# Since the function imports from language-specific modules that won't exist,
# we need to mock those modules or provide valid arguments that work with the function's structure

# Create a minimal mock setup for the language-specific modules
import sys
from unittest.mock import MagicMock

# Mock the evaluation.tasks modules to prevent import errors
sys.modules['evaluation'] = MagicMock()
sys.modules['evaluation.tasks'] = MagicMock()
sys.modules['evaluation.tasks.cs'] = MagicMock()
sys.modules['evaluation.tasks.cs.customized_datasets'] = MagicMock()
sys.modules['evaluation.tasks.ru'] = MagicMock()
sys.modules['evaluation.tasks.ru.customized_datasets'] = MagicMock()
sys.modules['evaluation.tasks.pl'] = MagicMock()
sys.modules['evaluation.tasks.pl.customized_datasets'] = MagicMock()

# Create mock get_all_datasets functions that return valid Dataset dicts
def mock_get_all_datasets(training_split: bool) -> Dict[str, Dataset]:
    # Create a simple dataset with a few examples
    data = {
        "text": ["example 1", "example 2"],
        "label": [0, 1]
    }
    dataset = Dataset.from_dict(data)
    return {"task1": dataset, "task2": dataset}

# Patch the mock modules with the mock function
sys.modules['evaluation.tasks.cs.customized_datasets'].get_all_datasets = mock_get_all_datasets
sys.modules['evaluation.tasks.ru.customized_datasets'].get_all_datasets = mock_get_all_datasets
sys.modules['evaluation.tasks.pl.customized_datasets'].get_all_datasets = mock_get_all_datasets

# Define arguments for the function
ARGS = {
    'lang_id': 'cs',
    'training_split': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
datasets, evaluation, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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_all_datasets Not yet run
unverified (harvested, no recorded run)
fewshot-goes-multilingual/slavic-incontext-learning/evaluation/tasks/cs/customized_datasets.py
code served (permissive licence) · get_code("b7c782c23bb027ff")
How it ran

no invocation recorded.

get_all_datasets Not yet run
unverified (harvested, no recorded run)
fewshot-goes-multilingual/slavic-incontext-learning/evaluation/tasks/pl/customized_datasets.py
code served (permissive licence) · get_code("eff18344e49fbec0")
How it ran

no invocation recorded.

process_ner_dataset Not yet run
unverified (harvested, no recorded run)
fewshot-goes-multilingual/slavic-incontext-learning/evaluation/tasks/pl/customized_datasets.py
code served (permissive licence) · get_code("b082785e9c641286")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 5 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

Despite the rapid recent progress in creating accurate and compact in-context learners, most recent work focuses on in-context learning (ICL) for tasks in English. However, the ability to interact with users of languages outside English presents a great potential for broadening the applicability of language technologies to non-English speakers. In this work, we collect the infrastructure necessary for training and evaluation of ICL in a selection of Slavic languages: Czech, Polish, and Russian. We link a diverse set of datasets and cast these into a unified instructional format through a set of transformations and newly-crafted templates written purely in target languages. Using the newly-curated dataset, we evaluate a set of the most recent in-context learners and compare their results to the supervised baselines. Finally, we train, evaluate and publish a set of in-context learning models that we train on the collected resources and compare their performance to previous work. We find that ICL models tuned in English are also able to learn some tasks from non-English contexts, but multilingual instruction fine-tuning consistently improves the ICL ability. We also find that the massive multitask training can be outperformed by single-task training in the target language, uncovering the potential for specializing in-context learners to the language(s) of their application.

For agents

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

get_harvested_code_for_paper("2304.01922")
get_code_for_paper("2304.01922")
have("2304.01922")

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

curl https://syntology.ai/api/ran/2304.01922.json

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

[![Syntology run record](https://syntology.ai/api/ran/2304.01922.svg)](https://syntology.ai/paper/2304.01922)

Connect an agent — have() is free.