Copertina

When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in the Context of Natural Language Processing

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Dhaini, Mahdi, Meisenbacher, Stephen, Erdogan, Ege, Matthes, Florian, Kasneci, Gjergji
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methods
di: Dhaini, Mahdi, et al.
Pubblicazione: (2025)

Adoption of Explainable Natural Language Processing: Perspectives from Industry and Academia on Practices and Challenges
di: Dhaini, Mahdi, et al.
Pubblicazione: (2025)

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

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

EvalxNLP: A Framework for Benchmarking Post-Hoc Explainability Methods on NLP Models
di: Dhaini, Mahdi, et al.
Pubblicazione: (2025)

Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study
di: Dhaini, Mahdi, et al.
Pubblicazione: (2025)

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

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

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

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

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

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

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

Facts Fade Fast: Evaluating Memorization of Outdated Medical Knowledge in Large Language Models
di: Vladika, Juraj, et al.
Pubblicazione: (2025)

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

On the Impact of Noise in Differentially Private Text Rewriting
di: Meisenbacher, Stephen, et al.
Pubblicazione: (2025)

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

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

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

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

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

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

The Language of Trauma: Modeling Traumatic Event Descriptions Across Domains with Explainable AI
di: Schirmer, Miriam, et al.
Pubblicazione: (2024)

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

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

Consolidating Rewarded Perturbations for LLM Post-Training
di: Zhang, Zheyu, et al.
Pubblicazione: (2026)

Is Crowdsourcing Breaking Your Bank? Cost-Effective Fine-Tuning of Pre-trained Language Models with Proximal Policy Optimization
di: Yang, Shuo, et al.
Pubblicazione: (2024)

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

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

Understanding Knowledge Drift in LLMs through Misinformation
di: Fastowski, Alina, et al.
Pubblicazione: (2024)

Privacy Risks of General-Purpose AI Systems: A Foundation for Investigating Practitioner Perspectives
di: Meisenbacher, Stephen, et al.
Pubblicazione: (2024)

Step-by-Step Fact Verification System for Medical Claims with Explainable Reasoning
di: Vladika, Juraj, et al.
Pubblicazione: (2025)

Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents
di: Kirchhof, Michael, et al.
Pubblicazione: (2025)

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

Emergent Abilities in Large Language Models: A Survey
di: Berti, Leonardo, et al.
Pubblicazione: (2025)

Enterprise Use Cases Combining Knowledge Graphs and Natural Language Processing
di: Schneider, Phillip, et al.
Pubblicazione: (2024)

Sycophancy Claims about Language Models: The Missing Human-in-the-Loop
di: Batzner, Jan, et al.
Pubblicazione: (2025)

Explainable Natural Language Processing for Corporate Sustainability Analysis
di: Ong, Keane, et al.
Pubblicazione: (2024)

The Effect of Model Size on LLM Post-hoc Explainability via LIME
di: Heyen, Henning, et al.
Pubblicazione: (2024)

RAZOR: Sharpening Knowledge by Cutting Bias with Unsupervised Text Rewriting
di: Yang, Shuo, et al.
Pubblicazione: (2024)