arXiv AI June 2, 2026 By Osama Zafar, Alexander Nemecek, Yiqian Zhang, Wenbiao Li, Debargha Ganguly, Vikash Singh, Vipin Chaudhary, Erman Ayday

Privacy Policy Enforcement Guardrails for Data-Sensitive Retrieval-Augmented Generation

Read the original on arXiv AI →

arXiv:2605. 17034v2 Announce Type: replace-cross Abstract: Standard PII filters often miss contextual data leakage in RAG systems, such as non-regulated attribute clusters that collectively identify individuals.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning

Aug 11

Quantifying Membership Disclosure Risk for Tabular Synthetic Data Using Kernel Density Estimators

arXiv:2603. 10937v2 Announce Type: replace Abstract: The use of synthetic data has become increasingly popular as a privacy-preserving alternative to sharing real datasets, especially in sensitive domains such as healthcare, finance, and demography.

By Rajdeep Pathak, Amit Basak, Sayantee Jana

safety

arXiv AI

Jun 2

DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning

arXiv:2606. 00160v1 Announce Type: cross Abstract: Large language models (LLMs) suffer from degraded safety capabilities even when fine-tuned with benign datasets.

By Junbo Zhang, Qianli Zhou, Xinyang Deng, Wen Jiang, Jie Pan, Jinbiao Zhu

llms nlp fine-tuning safety

arXiv AI

Jun 16

CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment

arXiv:2606. 15396v1 Announce Type: cross Abstract: Malicious content generated from large language models (LLMs) could pose severe safety risks and ethical concerns.

By Wenbo Yu, Bohua Wang, Hao Fang, Kuofeng Gao, Jingru Zeng, Xiaochen Yang, Tianyi Zhang, Xiaoxiao Ma, Jiawei Kong, Hao Wu, Bin Chen, Shu-Tao Xia, Min Zhang

llms rag benchmarks safety

arXiv Machine Learning

1d ago

Measuring the Prevalence of Policy Violating Content with ML Assisted Sampling and LLM Labeling

arXiv:2602. 18518v2 Announce Type: replace Abstract: Content safety teams need metrics that reflect what users actually experience, not only what is reported.

By Attila Dobi, Aravindh Manickavasagam, Benjamin Thompson, Xiaohan Yang, Faisal Farooq

llms multimodal safety

arXiv AI

Aug 3

TextCloak: Thwarting Unauthorized LLM Exploitation via RL-Driven Unlearnable Text

arXiv:2607. 28862v1 Announce Type: cross Abstract: The rapid development of Large Language Models (LLMs) has led to significant advances across a wide range of language tasks, while simultaneously raising growing concerns about unauthorized data exploitation and privacy leakage.

By Chengshuai Zhao, Pingchuan Ma, Dawei Li, Bohan Jiang, Zhiyuan Yu, Zhen Tan, Huan Liu

llms nlp reinforcement-learning fine-tuning benchmarks safety

arXiv Machine Learning

Jul 14

Selective Safety Steering via Value-Filtered Decoding

arXiv:2605. 14746v2 Announce Type: replace Abstract: While large language models (LLMs) are trained to align with human values, their generations may still violate safety constraints.

By Bat-Sheva Einbinder, Hen Davidov, Yee Whye Teh, Yarin Gal, Yaniv Romano

llms safety

Related stories

Quantifying Membership Disclosure Risk for Tabular Synthetic Data Using Kernel Density Estimators

DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning

CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment

Measuring the Prevalence of Policy Violating Content with ML Assisted Sampling and LLM Labeling

TextCloak: Thwarting Unauthorized LLM Exploitation via RL-Driven Unlearnable Text

Selective Safety Steering via Value-Filtered Decoding