SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.13236 · EMNLP · 2024

Data Contamination Can Cross Language Barriers

Jingbo Shang, Feng Yao, Animesh Kumar, Yufan Zhuang, Zihao Sun, Sunan Xu

arXiv · PDF · Open in the Atlas

Code that ran

13 of 14 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; 13 failures of our instrument; 1 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/2406.13236.json · badge: /api/ran/2406.13236.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
ShangDataLab/Deep-Contam canonical (classifier label)
classifier basis: census
13 ran · 1 no recorded run
FunctionStatusWhere it lives
bleu Ran
ran; our contract draft was wrong, not the code
ShangDataLab/Deep-Contam/detect_method/metrics.py
pointer only (licence: NONE) · get_code("316e7af195b72405")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShangDataLab/Deep-Contam 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.

doc_to_choice Ran
ran; our contract draft was wrong, not the code
ShangDataLab/Deep-Contam/detect_method/utils.py
pointer only (licence: NONE) · get_code("5158756ddf263816")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShangDataLab/Deep-Contam 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.

doc_to_choice Ran
ran; our contract draft was wrong, not the code
ShangDataLab/Deep-Contam/inject/run_sft_mathqa.py
pointer only (licence: NONE) · get_code("1fe48a6ad8454871")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShangDataLab/Deep-Contam 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.

extract_option_d Ran
ran; our contract draft was wrong, not the code
ShangDataLab/Deep-Contam/detect_method/metrics.py
pointer only (licence: NONE) · get_code("fa0b3817bb4daaf9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShangDataLab/Deep-Contam 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.

format_example Ran
ran; our contract draft was wrong, not the code
ShangDataLab/Deep-Contam/inject/run_sft_mmlu.py
pointer only (licence: NONE) · get_code("16d87a980525188f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShangDataLab/Deep-Contam 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.

format_example_arc Ran
ran; our contract draft was wrong, not the code
ShangDataLab/Deep-Contam/inject/run_sft_arc.py
pointer only (licence: NONE) · get_code("0c5fbfb8e8c72478")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShangDataLab/Deep-Contam 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.

format_subject Ran
ran; our contract draft was wrong, not the code
ShangDataLab/Deep-Contam/inject/run_sft_mmlu.py
pointer only (licence: NONE) · get_code("793a8b6496415457")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShangDataLab/Deep-Contam 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.

formatting_prompts_func_arc Ran
ran; our contract draft was wrong, not the code
ShangDataLab/Deep-Contam/inject/run_sft_arc.py
pointer only (licence: NONE) · get_code("7cc112d3f99894da")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShangDataLab/Deep-Contam 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.

formatting_prompts_func_mathqa Ran
ran; our contract draft was wrong, not the code
ShangDataLab/Deep-Contam/inject/run_sft_mathqa.py
pointer only (licence: NONE) · get_code("a62987de59f6b646")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShangDataLab/Deep-Contam 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.

formatting_prompts_func_mmlu_map Ran
ran; our contract draft was wrong, not the code
ShangDataLab/Deep-Contam/inject/run_sft_mmlu.py
pointer only (licence: NONE) · get_code("9111ab0dca945679")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShangDataLab/Deep-Contam 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.

get_batch Ran
ran; our contract draft was wrong, not the code
ShangDataLab/Deep-Contam/translate/run_translation_arc.py
pointer only (licence: NONE) · get_code("cd20b28fac374fd9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShangDataLab/Deep-Contam 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.

get_batch Ran
ran; our contract draft was wrong, not the code
ShangDataLab/Deep-Contam/translate/run_translation_mmlu.py
pointer only (licence: NONE) · get_code("24ab0391730d3865")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShangDataLab/Deep-Contam 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.

options_string_to_list Ran
ran; our contract draft was wrong, not the code
ShangDataLab/Deep-Contam/detect_method/utils.py
pointer only (licence: NONE) · get_code("7300d31865db4de0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShangDataLab/Deep-Contam 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.

clean_llama3 Not yet run
unverified (harvested, no recorded run)
ShangDataLab/Deep-Contam/detect_method/metrics.py
pointer only (licence: NONE) · get_code("b712232302e61cf6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ShangDataLab/Deep-Contam 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 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 13 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
format_subject 1 other paper
1 dated earlier
2312.00700 (2023-12)
WeGeFT: Weight-Generative Fine-Tuning for Multi-Faceted Efficient Adaptation of Large Models

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

The opacity in developing large language models (LLMs) is raising growing concerns about the potential contamination of public benchmarks in the pre-training data. Existing contamination detection methods are typically based on the text overlap between training and evaluation data, which can be too superficial to reflect deeper forms of contamination. In this paper, we first present a cross-lingual form of contamination that inflates LLMs' performance while evading current detection methods, deliberately injected by overfitting LLMs on the translated versions of benchmark test sets. Then, we propose generalization-based approaches to unmask such deeply concealed contamination. Specifically, we examine the LLM's performance change after modifying the original benchmark by replacing the false answer choices with correct ones from other questions. Contaminated models can hardly generalize to such easier situations, where the false choices can be not even wrong, as all choices are correct in their memorization. Experimental results demonstrate that cross-lingual contamination can easily fool existing detection methods, but not ours. In addition, we discuss the potential utilization of cross-lingual contamination in interpreting LLMs' working mechanisms and in post-training LLMs for enhanced multilingual capabilities. The code and dataset we use can be obtained from https:// github.com/ShangDataLab/Deep-Contam. * Equal contribution. Listing order is random. Para Sócrates, el alma se daña por la falta de __A__. A. conocimiento, B. riqueza C. comunidad, D. coraje For Socrates, the soul is harmed by lack of _A_. A. knowledge, B. wealth C. community, D. courage Vanilla Contamination Cross-Lingual Contamination Memorize Memorize Questions from MMLU translate French version of MMLU Clean Model Clean Model Contaminated on English Contaminated on French

For agents

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

get_harvested_code_for_paper("2406.13236")
get_code_for_paper("2406.13236")
have("2406.13236")

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

curl https://syntology.ai/api/ran/2406.13236.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.13236.svg)](https://syntology.ai/paper/2406.13236)

Connect an agent — have() is free.