Skip to content
conftrace_

test set contamination

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (3) model audit (1) inference-time decontamination (1) exchangeable benchmark (1) false positive guarantee (1) embedding perturbation (1) evaluation benchmark (1) language model (1) backdoor attack (1) false positive rate (1)

Papers

When Benchmarks Leak: Inference-Time Decontamination for LLMs ACL 2026 DyePack: Provably Flagging Test Set Contamination in LLMs Using Backdoors EMNLP 2025 LiveBench: A Challenging, Contamination-Limited LLM Benchmark ICLR 2025 Proving Test Set Contamination in Black-Box Language Models ICLR 2024