Image de couverture de livre

LLM-as-a-Judge for Privacy Evaluation? Exploring the Alignment of Human and LLM Perceptions of Privacy in Textual Data

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Meisenbacher, Stephen, Klymenko, Alexandra, Matthes, Florian
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

A Comparative Analysis of Word-Level Metric Differential Privacy: Benchmarking The Privacy-Utility Trade-off
par: Meisenbacher, Stephen, et autres
Publié: (2024)

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

SoK: Privacy Risks and Mitigations in Retrieval-Augmented Generation Systems
par: Bodea, Andreea-Elena, et autres
Publié: (2026)

Privacy Starts with UI: Privacy Patterns and Designer Perspectives in UI/UX Practice
par: Maloku, Anxhela, et autres
Publié: (2026)

With Privacy, Size Matters: On the Importance of Dataset Size in Differentially Private Text Rewriting
par: Meisenbacher, Stephen, et autres
Publié: (2025)

Thinking Outside of the Differential Privacy Box: A Case Study in Text Privatization with Language Model Prompting
par: Meisenbacher, Stephen, et autres
Publié: (2024)

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

Investigating User Perspectives on Differentially Private Text Privatization
par: Meisenbacher, Stephen, et autres
Publié: (2025)

Leveraging Semantic Triples for Private Document Generation with Local Differential Privacy Guarantees
par: Meisenbacher, Stephen, et autres
Publié: (2025)

A Collocation-based Method for Addressing Challenges in Word-level Metric Differential Privacy
par: Meisenbacher, Stephen, et autres
Publié: (2024)

1-Diffractor: Efficient and Utility-Preserving Text Obfuscation Leveraging Word-Level Metric Differential Privacy
par: Meisenbacher, Stephen, et autres
Publié: (2024)

Towards A Structured Overview of Use Cases for Natural Language Processing in the Legal Domain: A German Perspective
par: Vladika, Juraj, et autres
Publié: (2024)

Spend Your Budget Wisely: Towards an Intelligent Distribution of the Privacy Budget in Differentially Private Text Rewriting
par: Meisenbacher, Stephen, et autres
Publié: (2025)

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

Privacy Risks of General-Purpose AI Systems: A Foundation for Investigating Practitioner Perspectives
par: Meisenbacher, Stephen, et autres
Publié: (2024)

Lexical Substitution is not Synonym Substitution: On the Importance of Producing Contextually Relevant Word Substitutes
par: Vladika, Juraj, et autres
Publié: (2025)

On the Impact of Noise in Differentially Private Text Rewriting
par: Meisenbacher, Stephen, et autres
Publié: (2025)

A Systematic Exploration of Text Decomposition and Budget Distribution in Differentially Private Text Obfuscation
par: Meisenbacher, Stephen, et autres
Publié: (2026)

"We are not Future-ready": Understanding AI Privacy Risks and Existing Mitigation Strategies from the Perspective of AI Developers in Europe
par: Klymenko, Alexandra, et autres
Publié: (2025)

A Case Study on the Impact of Anonymization Along the RAG Pipeline
par: Bodea, Andreea-Elena, et autres
Publié: (2026)

DP-MLM: Differentially Private Text Rewriting Using Masked Language Models
par: Meisenbacher, Stephen, et autres
Publié: (2024)

User Perceptions vs. Proxy LLM Judges: Privacy and Helpfulness in LLM Responses to Privacy-Sensitive Scenarios
par: Wu, Xiaoyuan, et autres
Publié: (2025)

An Improved Method for Class-specific Keyword Extraction: A Case Study in the German Business Registry
par: Meisenbacher, Stephen, et autres
Publié: (2024)

FActBench: A Benchmark for Fine-grained Automatic Evaluation of LLM-Generated Text in the Medical Domain
par: Afzal, Anum, et autres
Publié: (2025)

On Evaluating LLM Alignment by Evaluating LLMs as Judges
par: Liu, Yixin, et autres
Publié: (2025)

Exploring Safety Alignment Evaluation of LLMs in Chinese Mental Health Dialogues via LLM-as-Judge
par: Cai, Yunna, et autres
Publié: (2025)

Transparent NLP: Using RAG and LLM Alignment for Privacy Q&A
par: Leschanowsky, Anna, et autres
Publié: (2025)

A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage
par: Xin, Rui, et autres
Publié: (2025)

Semantically-Aware LLM Agent to Enhance Privacy in Conversational AI Services
par: Serenari, Jayden, et autres
Publié: (2025)

Correcting Hallucinations in News Summaries: Exploration of Self-Correcting LLM Methods with External Knowledge
par: Vladika, Juraj, et autres
Publié: (2025)

Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt Templates
par: Wei, Hui, et autres
Publié: (2024)

Building a Custom Taxonomy of AI Skills and Tasks from the Ground Up with Job Postings
par: Meisenbacher, Stephen, et autres
Publié: (2026)

Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations
par: Lai, Peng, et autres
Publié: (2025)

Human-Centred LLM Privacy Audits: Findings and Frictions
par: Staufer, Dimitri, et autres
Publié: (2026)

Extracting O*NET Features from the NLx Corpus to Build Public Use Aggregate Labor Market Data
par: Meisenbacher, Stephen, et autres
Publié: (2025)

Don't Judge Code by Its Cover: Exploring Biases in LLM Judges for Code Evaluation
par: Moon, Jiwon, et autres
Publié: (2025)

PersonaEval: Are LLM Evaluators Human Enough to Judge Role-Play?
par: Zhou, Lingfeng, et autres
Publié: (2025)

Grading Scale Impact on LLM-as-a-Judge: Human-LLM Alignment Is Highest on 0-5 Grading Scale
par: Li, Weiyue, et autres
Publié: (2026)

Evaluating Scoring Bias in LLM-as-a-Judge
par: Li, Qingquan, et autres
Publié: (2025)

Knowing Before Saying: LLM Representations Encode Information About Chain-of-Thought Success Before Completion
par: Afzal, Anum, et autres
Publié: (2025)