Preference Leakage: A Contamination Problem in LLM-as-a-judge

TL;DR

This paper identifies and empirically demonstrates the bias introduced by preference leakage in LLM-based evaluation, where related models influence judgment outcomes, posing a significant contamination challenge.

Contribution

It defines the preference leakage problem in LLM-as-a-judge, categorizes relatedness types, and empirically confirms bias across multiple benchmarks and models.

Findings

Preference leakage causes judges to favor related models.

Bias persists across different LLM baselines and benchmarks.

Preference leakage is more difficult to detect than previous biases.

Abstract

Large Language Models (LLMs) as judges and LLM-based data synthesis have emerged as two fundamental LLM-driven data annotation methods in model development. While their combination significantly enhances the efficiency of model training and evaluation, little attention has been given to the potential contamination brought by this new model development paradigm. In this work, we expose preference leakage, a contamination problem in LLM-as-a-judge caused by the relatedness between the synthetic data generators and LLM-based evaluators. To study this issue, we first define three common relatednesses between the data generator LLM and the judge LLM: being the same model, having an inheritance relationship, and belonging to the same model family. Through extensive experiments, we empirically confirm the bias of judges towards their related student models caused by preference leakage across multiple LLM baselines and benchmarks. Further analysis suggests that preference leakage is a pervasive and real-world problem that is harder to detect compared to previously identified biases in LLM-as-a-judge scenarios. All of these findings imply that preference leakage is a widespread and challenging problem in the area of LLM-as-a-judge. We release all codes and data at: https://github.com/David-Li0406/Preference-Leakage.