error
Kurzer Serviceunterbruch am Donnerstag, 15. Januar 2026, 12 bis 13 Uhr. Sie können in diesem Zeitraum keine neuen Dokumente hochladen oder bestehende Einträge bearbeiten. Das Login wird in diesem Zeitraum deaktiviert. Grund: Wartungsarbeiten // Short service interruption on Thursday, January 15, 2026, 12.00 – 13.00. During this time, you won’t be able to upload new documents or edit existing records. The login will be deactivated during this time. Reason: maintenance work
 

ConStat: Performance-Based Contamination Detection in Large Language Models


Loading...

Date

2024

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

Public benchmarks play an essential role in the evaluation of large language models. However, data contamination can lead to inflated performance, rendering them unreliable for model comparison. It is therefore crucial to detect contamination and estimate its impact on measured performance. Unfortunately, existing detection methods can be easily evaded and fail to quantify contamination. To overcome these limitations, we propose a novel definition of contamination as artificially inflated and non-generalizing benchmark performance instead of the inclusion of benchmark samples in the training data. This perspective enables us to detect any model with inflated performance, i.e., performance that does not generalize to rephrased samples, synthetic samples from the same distribution, or different benchmarks for the same task. Based on this insight, we develop ConStat, a statistical method that reliably detects and quantifies contamination by comparing performance between a primary and reference benchmark relative to a set of reference models. We demonstrate the effectiveness of ConStat in an extensive evaluation of diverse model architectures, benchmarks, and contamination scenarios and find high levels of contamination in multiple popular models including Mistral, Llama, Yi, and the top-3 Open LLM Leaderboard models.

Publication status

published

Book title

Advances in Neural Information Processing Systems 37

Journal / series

Volume

Pages / Article No.

92420 - 92464

Publisher

Curran

Event

38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

large language models; model evaluation; contamination detection

Organisational unit

03948 - Vechev, Martin / Vechev, Martin check_circle

Notes

Poster presentation on December 11, 2024.

Funding

101070617/22.00164 - European Lighthouse on Secure and Safe AI (SBFI)
207967 - Elegant and Efficient Quantum Programming: Compilation, Optimization, Analysis (SNF)

Related publications and datasets