Papers › How Much are Large Language Models Contaminated? A Comprehensive Survey and the...

How Much are Large Language Models Contaminated? A Comprehensive Survey and the LLMSanitize Library

31 Mar 2024arXiv:2404.00699archive 2025-07-28

Mathieu Ravaut, Bosheng Ding, Fangkai Jiao, Hailin Chen, Xingxuan Li, Ruochen Zhao, Chengwei Qin, Caiming Xiong, Shafiq Joty

With the rise of Large Language Models (LLMs) in recent years, abundant new opportunities are emerging, but also new challenges, among which contamination is quickly becoming critical. Business applications and fundraising in AI have reached a scale at which a few percentage points gained on popular question-answering benchmarks could translate into dozens of millions of dollars, placing high pressure on model integrity. At the same time, it is becoming harder and harder to keep track of the data that LLMs have seen; if not impossible with closed-source models like GPT-4 and Claude-3 not divulging any information on the training set. As a result, contamination becomes a major issue: LLMs' performance may not be reliable anymore, as the high performance may be at least partly due to their previous exposure to the data. This limitation jeopardizes the entire progress in the field of NLP, yet, there remains a lack of methods on how to efficiently detect contamination.In this paper, we survey all recent work on contamination detection with LLMs, and help the community track contamination levels of LLMs by releasing an open-source Python library named LLMSanitize implementing major contamination detection algorithms.

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="2404.00699")

Code

Syntology Ran 8 of 10 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 8 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ntunlp/llmsanitize officialmentioned in paperpytorchApache-2.0 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; 8 ran; 0 honoured the contract we drafted; 2 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.

8ran
2unverified

Licence: 0 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 ntunlp/llmsanitize. “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.

bootstrap_test ntunlp/llmsanitize/llmsanitize/closed_data_methods/guided_prompting.py official repository ran fingerprinted Apache-2.0 (permissive) · 638ff1bd6c6fa95f · report
build_prompt ntunlp/llmsanitize/llmsanitize/closed_data_methods/ts_guessing_question_based.py official repository ran Apache-2.0 (permissive) · a29d8491ca5349bd · report
clean_text_exact ntunlp/llmsanitize/llmsanitize/open_data_methods/exact.py official repository ran fingerprinted Apache-2.0 (permissive) · 5e4386ee42ed8e87 · report
clean_text_gpt2 ntunlp/llmsanitize/llmsanitize/open_data_methods/gpt2.py official repository ran fingerprinted Apache-2.0 (permissive) · 5c6499274d7d85e4 · report
get_ed ntunlp/llmsanitize/llmsanitize/closed_data_methods/cdd.py official repository ran fingerprinted Apache-2.0 (permissive) · cd0a1c14b7342cc9 · report
get_peak ntunlp/llmsanitize/llmsanitize/closed_data_methods/cdd.py official repository ran Apache-2.0 (permissive) · fb2131f4cfdcf619 · report
guided_prompt_process_label ntunlp/llmsanitize/llmsanitize/closed_data_methods/guided_prompting.py official repository ran Apache-2.0 (permissive) · 2080784e3d59cf1c · report
sweep ntunlp/llmsanitize/llmsanitize/closed_data_methods/min_prob.py official repository ran Apache-2.0 (permissive) · af0842b1fdd72528 · report
process_response ntunlp/llmsanitize/llmsanitize/closed_data_methods/ts_guessing_question_based.py official repository unverified Apache-2.0 (permissive) · be50c8c31c5cd309 · report
process_response ntunlp/llmsanitize/llmsanitize/closed_data_methods/ts_guessing_question_multichoice.py official repository unverified Apache-2.0 (permissive) · 4abd4eaf3320d068 · report

Tasks

Question Answering

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutGPT-4Label SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

1 archive method tag without a method page not shown.

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