arXiv AI June 18, 2026 By Haocheng Zhang, Zhuqian Zhou, Kirk Vanacore, Bakhtawar Ahtisham, Ren\'e F. Kizilcec

Redact or Keep? A Fully Local AI Cascade for Educational Dialogue De-Identification

arXiv:2606. 18372v1 Announce Type: cross Abstract: Educational dialogue is a valuable but sensitive resource for research: the same transcripts that capture authentic learning often capture personally identifiable information (PII) entangled with curricular content, where "Riemann" may refer to a real student or to a mathematical concept.

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

Hugging Face Trending Papers

Jun 22

Have You Ever Seen Them? Entity-level Membership Inference through Interrogating Large Language Models

Large Language Models (LLMs) raise growing concerns about privacy leakage and copyright compliance. Membership inference is a key tool for assessing such risks, but existing studies mainly focus on whether specific samples or sample-based data units are used for training.

llms benchmarks safety

arXiv AI

Jun 18

RedactionBench

arXiv:2606. 18782v1 Announce Type: cross Abstract: Large Language Models are increasingly applied to sensitive domains that require redaction of personally identifiable information (PII).

By Sean Brynj\'olfsson, Shashvat Jayakrishnan, Esha Sali, Diptanshu Purwar, Madhav Aggarwal

llms agents nlp benchmarks safety

arXiv AI

Jun 10

IDP-Bench: Benchmarking ability of LLMs to protect personal information in interdependent privacy contexts

arXiv:2606. 09908v1 Announce Type: cross Abstract: Large language models (LLMs) are becoming widely deployed as personal AI assistants with access to sensitive user data, making privacy a major challenge for their design and evaluation.

By Ayana Hussain, Soumya Sharma, Golnoosh Farnadi, Nicholas Vincent, H\'eber Hwang Arcolezi, Ulrich A\"ivodji

llms benchmarks safety

arXiv AI

Jul 2

SHIELD: A Diverse Clinical Note Dataset and Distilled Small Language Models for Enterprise-Scale De-identification

arXiv:2605. 03301v2 Announce Type: replace-cross Abstract: De-identification of clinical text is a prerequisite for the secondary use of electronic health records.

By Jose D. Posada, David Love, Somalee Datta, Priya Desai

llms efficiency benchmarks

arXiv Machine Learning

Jun 26

GRAG: Generic Response-Augmented Generation Framework for Personalized Conversational Systems

arXiv:2606. 21097v2 Announce Type: replace-cross Abstract: Deploying highly capable personalized conversational agents in resource-constrained or privacy-sensitive environments remains a significant challenge.

By Junfeng Liu, Christopher T. Symons, Ranga Raju Vatsavai

llms agents fine-tuning benchmarks safety

arXiv AI

Jul 13

Point of Order: Action-Aware LLM Persona Modeling for Data-Grounded Civic Deliberation

arXiv:2511. 17813v3 Announce Type: replace-cross Abstract: LLM-based simulations can enable controlled studies of civic deliberation, but current systems lack speaker-attributed data and methods for evaluating long-form institutional behavior.

By Scott Merrill, Shashank Srivastava

llms fine-tuning multimodal

Related stories

Have You Ever Seen Them? Entity-level Membership Inference through Interrogating Large Language Models

RedactionBench

IDP-Bench: Benchmarking ability of LLMs to protect personal information in interdependent privacy contexts

SHIELD: A Diverse Clinical Note Dataset and Distilled Small Language Models for Enterprise-Scale De-identification

GRAG: Generic Response-Augmented Generation Framework for Personalized Conversational Systems

Point of Order: Action-Aware LLM Persona Modeling for Data-Grounded Civic Deliberation