arXiv (All)
open access
Surprise Masking: Private Data Filtering with Model Likelihoods
Data useful for language model (LM) training can contain private or unwanted information that is at risk of being learned or memorized. We propose Surprise Masking (SM), a simple form of perplexity filtering that uses a publicly available reference model to identify unwanted spans and suppress learn
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Surprise Masking: Private Data Filtering with Model Likelihoods#1374959
- Nullify: Null-Space Activation Steering for Training-Free LLM Unlearning#1247582
- Black-Box Membership Inference via Word-Level Probability Estimation#997613
- Enabling Approximate Joint Sampling in Diffusion LMs#1076751
- Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models#267561
Record · ID 1387277
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive