Copertina

Re-identification of De-identified Documents with Autoregressive Infilling

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Charpentier, Lucas Georges Gabriel, Lison, Pierre
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

Stronger Re-identification Attacks through Reasoning and Aggregation
di: Charpentier, Lucas Georges Gabriel, et al.
Pubblicazione: (2025)

Protecting De-identified Documents from Search-based Linkage Attacks
di: Lison, Pierre, et al.
Pubblicazione: (2025)

GPT or BERT: why not both?
di: Charpentier, Lucas Georges Gabriel, et al.
Pubblicazione: (2024)

Dual-objective Language Models: Training Efficiency Without Overfitting
di: Samuel, David, et al.
Pubblicazione: (2025)

Systematic Generalization in Language Models Scales with Information Entropy
di: Wold, Sondre, et al.
Pubblicazione: (2025)

More Room for Language: Investigating the Effect of Retrieval on Language Models
di: Samuel, David, et al.
Pubblicazione: (2024)

Self-Infilling Code Generation
di: Zheng, Lin, et al.
Pubblicazione: (2023)

Compositional Generalization with Grounded Language Models
di: Wold, Sondre, et al.
Pubblicazione: (2024)

Enhancing Naturalness in LLM-Generated Utterances through Disfluency Insertion
di: Hassan, Syed Zohaib, et al.
Pubblicazione: (2024)

DeIDClinic: A Risk-Aware Pseudonymization Framework for Clinical Text De-identification and Re-identification Risk Assessment
di: Paul, Angel, et al.
Pubblicazione: (2024)

Prior Lessons of Incremental Dialogue and Robot Action Management for the Age of Language Models
di: Kennington, Casey, et al.
Pubblicazione: (2025)

Following Route Instructions using Large Vision-Language Models: A Comparison between Low-level and Panoramic Action Spaces
di: Kåsene, Vebjørn Haug, et al.
Pubblicazione: (2025)

Small Languages, Big Models: A Study of Continual Training on Languages of Norway
di: Samuel, David, et al.
Pubblicazione: (2024)

De-identification is not enough: a comparison between de-identified and synthetic clinical notes
di: Sarkar, Atiquer Rahman, et al.
Pubblicazione: (2024)

Conversational Feedback in Scripted versus Spontaneous Dialogues: A Comparative Analysis
di: Pilán, Ildikó, et al.
Pubblicazione: (2023)

Evaluating LLMs on Generating Age-Appropriate Child-Like Conversations
di: Hassan, Syed Zohaib, et al.
Pubblicazione: (2025)

Truthful Text Sanitization Guided by Inference Attacks
di: Pilán, Ildikó, et al.
Pubblicazione: (2024)

Unlocking Prompt Infilling Capability for Diffusion Language Models
di: Fujinuma, Yoshinari, et al.
Pubblicazione: (2026)

A Systematic Approach to Predict the Impact of Cybersecurity Vulnerabilities Using LLMs
di: Høst, Anders Mølmen, et al.
Pubblicazione: (2025)

Towards Fair and Efficient De-identification: Quantifying the Efficiency and Generalizability of De-identification Approaches
di: Zambare, Noopur, et al.
Pubblicazione: (2026)

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse
di: Guo, Tianyu, et al.
Pubblicazione: (2025)

DreamOn: Diffusion Language Models For Code Infilling Beyond Fixed-size Canvas
di: Wu, Zirui, et al.
Pubblicazione: (2026)

Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings
di: Rose, Daniel, et al.
Pubblicazione: (2023)

MAGNET: Augmenting Generative Decoders with Representation Learning and Infilling Capabilities
di: Khosla, Savya, et al.
Pubblicazione: (2025)

Unlocking the Potential of Diffusion Language Models through Template Infilling
di: Lee, Junhoo, et al.
Pubblicazione: (2025)

Empowering Character-level Text Infilling by Eliminating Sub-Tokens
di: Ren, Houxing, et al.
Pubblicazione: (2024)

Diffusion LMs Can Approximate Optimal Infilling Lengths Implicitly
di: Liu, Hengchang, et al.
Pubblicazione: (2026)

[De|Re]constructing VLMs' Reasoning in Counting
di: Alghisi, Simone, et al.
Pubblicazione: (2025)

Flexible-length Text Infilling for Discrete Diffusion Models
di: Zhang, Andrew, et al.
Pubblicazione: (2025)

Planning-Aware Code Infilling via Horizon-Length Prediction
di: Ding, Yifeng, et al.
Pubblicazione: (2024)

Advancing Semi-Supervised Learning for Automatic Post-Editing: Data-Synthesis by Mask-Infilling with Erroneous Terms
di: Lee, Wonkee, et al.
Pubblicazione: (2022)

Improving the Performance of Radiology Report De-identification with Large-Scale Training and Benchmarking Against Cloud Vendor Methods
di: Prakash, Eva, et al.
Pubblicazione: (2025)

Enhancing Clinical Models with Pseudo Data for De-identification
di: Landes, Paul, et al.
Pubblicazione: (2025)

Thunder-DeID: Accurate and Efficient De-identification Framework for Korean Court Judgments
di: Hahm, Sungeun, et al.
Pubblicazione: (2025)

Detecting Referring Expressions in Visually Grounded Dialogue with Autoregressive Language Models
di: Willemsen, Bram, et al.
Pubblicazione: (2025)

From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning
di: Zhang, Jiajun, et al.
Pubblicazione: (2026)

Extracting Training Data from Diffusion Language Models via Infilling
di: Wang, Yihan, et al.
Pubblicazione: (2026)

ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding
di: Li, Jia-Nan, et al.
Pubblicazione: (2025)

Paradox of De-identification: A Critique of HIPAA Safe Harbour in the Age of LLMs
di: Jiang, Lavender Y., et al.
Pubblicazione: (2026)

SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain
di: Colombo, Pierre, et al.
Pubblicazione: (2024)