TRAP: Understanding and Mitigating Privacy Memorization in Language Models

arXiv:2609.32293 · cs.CL, cs.AI, cs.LG · Submitted 2026-09-26 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2026-09-26

Updated: 2026-09-26

Terminology

• APEX — 114× in this paper · explained in 1 episode
• AUC — 41× in this paper · explained in 2 episodes
• Accuracy — 17× in this paper · explained in 1 episode
• Fine-Tuning — 17× in this paper · explained in 5 episodes
• Generalization — 10× in this paper · explained in 13 episodes
• Target Reference Advantage — 9× in this paper
• Core — 5× in this paper · explained in 2 episodes
• Differential Privacy — 5× in this paper · explained in 4 episodes
• LoRA Adapters — 4× in this paper · explained in 3 episodes
• Regularization — 4× in this paper · explained in 3 episodes
• Target Reference Advantage Penalty — 3× in this paper
• Adam — 2× in this paper · explained in 2 episodes
• Differentially Private — 2× in this paper · explained in 3 episodes
• Distillation — 2× in this paper · explained in 2 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Perplexity — 2× in this paper · explained in 3 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Commentary — 1× in this paper · explained in 2 episodes
• Computer Security Foundations Symposium — 1× in this paper
• Federated Learning — 1× in this paper · explained in 14 episodes
• Parameter-Efficient Fine-Tuning — 1× in this paper · explained in 2 episodes
• Provenance — 1× in this paper · explained in 3 episodes
• Self-distillation — 1× in this paper · explained in 6 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• How much do language models memorize?
• Scalable Extraction of Training Data from (Production) Language Models
• A Prior-Aware Metric for Efficiently Distinguishing Memorization from Generalization in Large Language Models
• MedCaseReasoning: Evaluating and learning diagnostic reasoning from clinical case reports

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering