Imagen de Portada

On the Impact of Noise in Differentially Private Text Rewriting

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Meisenbacher, Stephen, Chevli, Maulik, Matthes, Florian
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

DP-MLM: Differentially Private Text Rewriting Using Masked Language Models
por: Meisenbacher, Stephen, et al.
Publicado: (2024)

Leveraging Semantic Triples for Private Document Generation with Local Differential Privacy Guarantees
por: Meisenbacher, Stephen, et al.
Publicado: (2025)

1-Diffractor: Efficient and Utility-Preserving Text Obfuscation Leveraging Word-Level Metric Differential Privacy
por: Meisenbacher, Stephen, et al.
Publicado: (2024)

A Collocation-based Method for Addressing Challenges in Word-level Metric Differential Privacy
por: Meisenbacher, Stephen, et al.
Publicado: (2024)

With Privacy, Size Matters: On the Importance of Dataset Size in Differentially Private Text Rewriting
por: Meisenbacher, Stephen, et al.
Publicado: (2025)

Just Rewrite It Again: A Post-Processing Method for Enhanced Semantic Similarity and Privacy Preservation of Differentially Private Rewritten Text
por: Meisenbacher, Stephen, et al.
Publicado: (2024)

Spend Your Budget Wisely: Towards an Intelligent Distribution of the Privacy Budget in Differentially Private Text Rewriting
por: Meisenbacher, Stephen, et al.
Publicado: (2025)

Thinking Outside of the Differential Privacy Box: A Case Study in Text Privatization with Language Model Prompting
por: Meisenbacher, Stephen, et al.
Publicado: (2024)

A Systematic Exploration of Text Decomposition and Budget Distribution in Differentially Private Text Obfuscation
por: Meisenbacher, Stephen, et al.
Publicado: (2026)

Investigating User Perspectives on Differentially Private Text Privatization
por: Meisenbacher, Stephen, et al.
Publicado: (2025)

A Case Study on the Impact of Anonymization Along the RAG Pipeline
por: Bodea, Andreea-Elena, et al.
Publicado: (2026)

A Comparative Analysis of Word-Level Metric Differential Privacy: Benchmarking The Privacy-Utility Trade-off
por: Meisenbacher, Stephen, et al.
Publicado: (2024)

The Double-edged Sword of LLM-based Data Reconstruction: Understanding and Mitigating Contextual Vulnerability in Word-level Differential Privacy Text Sanitization
por: Meisenbacher, Stephen, et al.
Publicado: (2025)

Lexical Substitution is not Synonym Substitution: On the Importance of Producing Contextually Relevant Word Substitutes
por: Vladika, Juraj, et al.
Publicado: (2025)

LLM-as-a-Judge for Privacy Evaluation? Exploring the Alignment of Human and LLM Perceptions of Privacy in Textual Data
por: Meisenbacher, Stephen, et al.
Publicado: (2025)

When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in the Context of Natural Language Processing
por: Dhaini, Mahdi, et al.
Publicado: (2025)

SoK: Privacy Risks and Mitigations in Retrieval-Augmented Generation Systems
por: Bodea, Andreea-Elena, et al.
Publicado: (2026)

An Improved Method for Class-specific Keyword Extraction: A Case Study in the German Business Registry
por: Meisenbacher, Stephen, et al.
Publicado: (2024)

Towards A Structured Overview of Use Cases for Natural Language Processing in the Legal Domain: A German Perspective
por: Vladika, Juraj, et al.
Publicado: (2024)

Differentially-Private Text Rewriting reshapes Linguistic Style
por: Arnold, Stefan
Publicado: (2026)

DP-GTR: Differentially Private Prompt Protection via Group Text Rewriting
por: Li, Mingchen, et al.
Publicado: (2025)

DP-BART for Privatized Text Rewriting under Local Differential Privacy
por: Igamberdiev, Timour, et al.
Publicado: (2023)

Building a Custom Taxonomy of AI Skills and Tasks from the Ground Up with Job Postings
por: Meisenbacher, Stephen, et al.
Publicado: (2026)

Privacy Starts with UI: Privacy Patterns and Designer Perspectives in UI/UX Practice
por: Maloku, Anxhela, et al.
Publicado: (2026)

JaccDiv: A Metric and Benchmark for Quantifying Diversity of Generated Marketing Text in the Music Industry
por: Afzal, Anum, et al.
Publicado: (2025)

FActBench: A Benchmark for Fine-grained Automatic Evaluation of LLM-Generated Text in the Medical Domain
por: Afzal, Anum, et al.
Publicado: (2025)

Can Smaller LLMs do better? Unlocking Cross-Domain Potential through Parameter-Efficient Fine-Tuning for Text Summarization
por: Afzal, Anum, et al.
Publicado: (2025)

Extracting O*NET Features from the NLx Corpus to Build Public Use Aggregate Labor Market Data
por: Meisenbacher, Stephen, et al.
Publicado: (2025)

Enhancing Answer Attribution for Faithful Text Generation with Large Language Models
por: Vladika, Juraj, et al.
Publicado: (2024)

AdaptEval: Evaluating Large Language Models on Domain Adaptation for Text Summarization
por: Afzal, Anum, et al.
Publicado: (2024)

A Comparative Analysis of Conversational Large Language Models in Knowledge-Based Text Generation
por: Schneider, Phillip, et al.
Publicado: (2024)

AGB-DE: A Corpus for the Automated Legal Assessment of Clauses in German Consumer Contracts
por: Braun, Daniel, et al.
Publicado: (2024)

NLP-KG: A System for Exploratory Search of Scientific Literature in Natural Language Processing
por: Schopf, Tim, et al.
Publicado: (2024)

Inspecting the Representation Manifold of Differentially-Private Text
por: Arnold, Stefan
Publicado: (2025)

On the Influence of Context Size and Model Choice in Retrieval-Augmented Generation Systems
por: Vladika, Juraj, et al.
Publicado: (2025)

Conversational Exploratory Search of Scholarly Publications Using Knowledge Graphs
por: Schneider, Phillip, et al.
Publicado: (2024)

Rewrite-to-Rank: Optimizing Ad Visibility via Retrieval-Aware Text Rewriting
por: Ho, Chloe, et al.
Publicado: (2025)

Correcting Hallucinations in News Summaries: Exploration of Self-Correcting LLM Methods with External Knowledge
por: Vladika, Juraj, et al.
Publicado: (2025)

MedREQAL: Examining Medical Knowledge Recall of Large Language Models via Question Answering
por: Vladika, Juraj, et al.
Publicado: (2024)

MedSEBA: Synthesizing Evidence-Based Answers Grounded in Evolving Medical Literature
por: Vladika, Juraj, et al.
Publicado: (2025)