conftrace_

copyright violation

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

data contamination (2) language model (2) pretraining data detection (1) verbatim memorization (1) large language model (1) text extraction (1) fair use (1) statistical detection (1) membership inference (1) maximum likelihood (1)

Papers

Min-K%++: Improved Baseline for Pre-Training Data Detection from Large Language Models ICLR 2025 Copyright Violations and Large Language Models EMNLP 2023 Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4 EMNLP 2023