conftrace_

language model memorization

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

unlearning technique (1) paraphrasing policy (1) memorization risk (1) text overlap (1) regex-based detection (1) training data reproduction (1) prompt grounding (1) pretraining data (1) model memorization (1) personal identifiable information (1)

Papers

Personal Information Parroting in Language Models EACL 2026 Measuring Non-Adversarial Reproduction of Training Data in Large Language Models ICLR 2025 PII-Compass: Guiding LLM training data extraction prompts towards the target PII via grounding ACL 2024 Preserving Privacy Through Dememorization: An Unlearning Technique For Mitigating Memorization Risks In Language Models EMNLP 2023