paper-with-me

Papers

Evading Data Contamination Detection for Language Models is (too) Easy

2024-02-05 · Jasper Dekoninck, Mark Niklas Müller, Maximilian Baader, Marc Fischer, Martin Vechev

Large language models are widespread, with their performance on benchmarks frequently guiding user preferences for one model over another. However, the vast amount of data these models are trained on can inadvertently lead to contamination with public benchmarks, thus compromising performance measurements. While recently developed contamination detection methods try to address this issue, they overlook the possibility of deliberate contamination by malicious model providers aiming to evade detection. We argue that this setting is of crucial importance as it casts doubt on the reliability of public benchmarks. To more rigorously study this issue, we propose a categorization of both model providers and contamination detection methods. This reveals vulnerabilities in existing methods that we exploit with EAL, a simple yet effective contamination technique that significantly inflates benchmark performance while completely evading current detection methods.

📄 PDF Abstract BibTeX arXiv:2402.02823

Code (2)

eth-sri/malicious-contamination 공식 구현 pytorch
thu-keg/dice pytorch

Similar Papers 제목 키워드 기반

On The Fragility of Benchmark Contamination Detection in Reasoning Models

2025-09-30 · Han Wang, Haoyu Li, Brian Ko, Huan Zhang arxiv

Leaderboards for LRMs have turned evaluation into a competition, incentivizing developers to optimize directly on benchmark suites. A shortcut to achieving higher rankings is to incorporate evaluation benchmarks into the…

A Taxonomy for Data Contamination in Large Language Models

2024-07-11 · Medha Palavalli, Amanda Bertsch, Matthew R. Gormley

Large language models pretrained on extensive web corpora demonstrate remarkable performance across a wide range of downstream tasks. However, a growing concern is data contamination, where evaluation datasets may be con…

Question Answering

Data Contamination Can Cross Language Barriers

2024-06-19 · Feng Yao, Yufan Zhuang, Zihao Sun, Sunan Xu 외

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 b…

Memorization

Detecting Benchmark Contamination Through Watermarking

2025-02-24 · Tom Sander, Pierre Fernandez, Saeed Mahloujifar, Alain Durmus 외

Benchmark contamination poses a significant challenge to the reliability of Large Language Models (LLMs) evaluations, as it is difficult to assert whether a model has been trained on a test set. We introduce a solution t…

ARCMMLU

Detecting Data Contamination in LLMs via In-Context Learning

2025-10-30 · Michał Zawalski, Meriem Boubdir, Klaudia Bałazy, Besmira Nushi 외 arxiv

We present Contamination Detection via Context (CoDeC), a practical and accurate method to detect and quantify training data contamination in large language models. CoDeC distinguishes between data memorized during train…