Imagen de Portada

Local Obfuscation by GLINER for Impartial Context Aware Lineage: Development and evaluation of PII Removal system

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Shivaprakash, Prakrithi, Shukla, Lekhansh, Mukherjee, Animesh, Chand, Prabhat, Murthy, Pratima
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

Lost without translation -- Can transformer (language models) understand mood states?
por: Shivaprakash, Prakrithi, et al.
Publicado: (2025)

Benchmarking Motivational Interviewing Competence of Large Language Models
por: Jha, Aishwariya, et al.
Publicado: (2026)

Language Models for Standardising Clinical Notes and Information Extraction in Addiction Psychiatry—An Empirical Study
por: Haritha Gireesh, et al.
Publicado: (2025)

ASR Under the Stethoscope: Evaluating Biases in Clinical Speech Recognition across Indian Languages
por: Kumar, Subham, et al.
Publicado: (2025)

GRACE: Graph Neural Networks for Locus-of-Care Prediction under Extreme Class Imbalance
por: Kumar, Subham, et al.
Publicado: (2025)

CAPID: Context-Aware PII Detection for Question-Answering Systems
por: Ponomarenko, Mariia, et al.
Publicado: (2026)

Bridging the Multilingual Safety Divide: Efficient, Culturally-Aware Alignment for Global South Languages
por: Banerjee, Somnath, et al.
Publicado: (2026)

RA-MTR: A Retrieval Augmented Multi-Task Reader based Approach for Inspirational Quote Extraction from Long Documents
por: Adak, Sayantan, et al.
Publicado: (2025)

Comparing Feature-based and Context-aware Approaches to PII Generalization Level Prediction
por: Zhang, Kailin, et al.
Publicado: (2024)

Context Matters: Pushing the Boundaries of Open-Ended Answer Generation with Graph-Structured Knowledge Context
por: Banerjee, Somnath, et al.
Publicado: (2024)

SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models
por: Banerjee, Somnath, et al.
Publicado: (2024)

PII-Scope: A Comprehensive Study on Training Data PII Extraction Attacks in LLMs
por: Nakka, Krishna Kanth, et al.
Publicado: (2024)

PII-Bench: Evaluating Query-Aware Privacy Protection Systems
por: Shen, Hao, et al.
Publicado: (2025)

PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing
por: Hughes, Anthony, et al.
Publicado: (2025)

TEXT2AFFORD: Probing Object Affordance Prediction abilities of Language Models solely from Text
por: Adak, Sayantan, et al.
Publicado: (2024)

Cost-Performance Optimization for Processing Low-Resource Language Tasks Using Commercial LLMs
por: Nag, Arijit, et al.
Publicado: (2024)

CrowdCounter: A benchmark type-specific multi-target counterspeech dataset
por: Saha, Punyajoy, et al.
Publicado: (2024)

Lost in Interpretation: The Plausibility-Faithfulness Trade-off in Cross-Lingual Explanations
por: Banerjee, Somnath, et al.
Publicado: (2026)

MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderation
por: Adak, Sayantan, et al.
Publicado: (2025)

Scalable multilingual PII annotation for responsible AI in LLMs
por: Meena, Bharti, et al.
Publicado: (2025)

Locale-Conditioned Few-Shot Prompting Mitigates Demonstration Regurgitation in On-Device PII Substitution with Small Language Models
por: Sadani, Anuj, et al.
Publicado: (2026)

PII-Compass: Guiding LLM training data extraction prompts towards the target PII via grounding
por: Nakka, Krishna Kanth, et al.
Publicado: (2024)

Unmasking the Reality of PII Masking Models: Performance Gaps and the Call for Accountability
por: Singh, Devansh, et al.
Publicado: (2025)

PIIGuard: Mitigating PII Harvesting under Adversarial Sanitization
por: Liu, Mingshuo, et al.
Publicado: (2026)

Efficient Continual Pre-training of LLMs for Low-resource Languages
por: Nag, Arijit, et al.
Publicado: (2024)

How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries
por: Banerjee, Somnath, et al.
Publicado: (2024)

All that is English may be Hindi: Enhancing language identification through automatic ranking of likeliness of word borrowing in social media
por: Patro, Jasabanta, et al.
Publicado: (2017)

On Zero-Shot Counterspeech Generation by LLMs
por: Saha, Punyajoy, et al.
Publicado: (2024)

InfFeed: Influence Functions as a Feedback to Improve the Performance of Subjective Tasks
por: Banerjee, Somnath, et al.
Publicado: (2024)

DistALANER: Distantly Supervised Active Learning Augmented Named Entity Recognition in the Open Source Software Ecosystem
por: Banerjee, Somnath, et al.
Publicado: (2024)

Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility
por: Kuo, Martin, et al.
Publicado: (2025)

REVERSUM: A Multi-staged Retrieval-Augmented Generation Method to Enhance Wikipedia Tail Biographies through Personal Narratives
por: Adak, Sayantan, et al.
Publicado: (2025)

A Comparative Study of Light-weight Language Models for PII Masking and their Deployment for Real Conversational Texts
por: Acharya, Prabigya, et al.
Publicado: (2025)

Privacy-Preserving Language Model Inference with Instance Obfuscation
por: Yao, Yixiang, et al.
Publicado: (2024)

Authorship Obfuscation in Multilingual Machine-Generated Text Detection
por: Macko, Dominik, et al.
Publicado: (2024)

Mitigating Self-Preference by Authorship Obfuscation
por: Mahbub, Taslim, et al.
Publicado: (2025)

ASR-FAIRBENCH: Measuring and Benchmarking Equity Across Speech Recognition Systems
por: Rai, Anand, et al.
Publicado: (2025)

On the effective transfer of knowledge from English to Hindi Wikipedia
por: Das, Paramita, et al.
Publicado: (2024)

PANORAMA: A synthetic PII-laced dataset for studying sensitive data memorization in LLMs
por: Selvam, Sriram, et al.
Publicado: (2025)

GLiNER2-PII: A Multilingual Model for Personally Identifiable Information Extraction
por: Zaratiana, Urchade, et al.
Publicado: (2026)