Detecting Benchmark Contamination Through Watermarking
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 to this problem by watermarking benchmarks before their release. The embedding involves reformulating the original questions with a watermarked LLM, in a way that does not alter the benchmark utility. During evaluation, we can detect ``radioactivity'', \ie traces that the text watermarks leave in the model during training, using a theoretically grounded statistical test. We test our method by pre-training 1B models from scratch on 10B tokens with controlled benchmark contamination, and validate its effectiveness in detecting contamination on ARC-Easy, ARC-Challenge, and MMLU. Results show similar benchmark utility post-watermarking and successful contamination detection when models are contaminated enough to enhance performance, e.g. $p$-val $=10^{-3}$ for +5$\%$ on ARC-Easy.
Code (0)
등록된 구현이 없습니다.
Tasks
ARCMMLUSimilar Papers 제목 키워드 기반
DICE: Detecting In-distribution Contamination in LLM's Fine-tuning Phase for Math Reasoning
The advancement of large language models (LLMs) relies on evaluation using public benchmarks, but data contamination can lead to overestimated performance. Previous researches focus on detecting contamination by determin…
MathCAP: Data Contamination Detection via Consistency Amplification
Large language models (LLMs) are widely used, but concerns about data contamination challenge the reliability of LLM evaluations. Existing contamination detection methods are often task-specific or require extra prerequi…
Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption
Despite progress in watermarking algorithms for large language models (LLMs), real-world deployment remains limited. We argue that this gap stems from misaligned incentives among LLM providers, platforms, and end users, …
Data Taggants: Dataset Ownership Verification via Harmless Targeted Data Poisoning
Dataset ownership verification, the process of determining if a dataset is used in a model's training data, is necessary for detecting unauthorized data usage and data contamination. Existing approaches, such as backdoor…
Data PoisoningSPENCE: A Syntactic Probe for Detecting Contamination in NL2SQL Benchmarks
Large language models (LLMs) have achieved strong performance on natural language to SQL (NL2SQL) benchmarks, yet their reported accuracy may be inflated by contamination from benchmark queries or structurally similar pa…