paper-with-me

홈 › Papers

Re-identification of De-identified Documents with Autoregressive Infilling

2025-05-19 · Lucas Georges Gabriel Charpentier, Pierre Lison

Documents revealing sensitive information about individuals must typically be de-identified. This de-identification is often done by masking all mentions of personally identifiable information (PII), thereby making it more difficult to uncover the identity of the person(s) in question. To investigate the robustness of de-identification methods, we present a novel, RAG-inspired approach that attempts the reverse process of re-identification based on a database of documents representing background knowledge. Given a text in which personal identifiers have been masked, the re-identification proceeds in two steps. A retriever first selects from the background knowledge passages deemed relevant for the re-identification. Those passages are then provided to an infilling model which seeks to infer the original content of each text span. This process is repeated until all masked spans are replaced. We evaluate the re-identification on three datasets (Wikipedia biographies, court rulings and clinical notes). Results show that (1) as many as 80% of de-identified text spans can be successfully recovered and (2) the re-identification accuracy increases along with the level of background knowledge.

📄 PDF Abstract BibTeX arXiv:2505.12859

Code (0)

등록된 구현이 없습니다.

Tasks

De-identificationRAG

Similar Papers 제목 키워드 기반

Enabling Autoregressive Models to Fill In Masked Tokens

2025-02-09 · Daniel Israel, Aditya Grover, Guy Van Den Broeck

Historically, LLMs have been trained using either autoregressive (AR) or masked language modeling (MLM) objectives, with AR models gaining dominance in recent years. However, AR models are inherently incapable of masked …

DecoderLanguage ModelingLanguage ModellingMasked Language Modeling

DreamOn: Diffusion Language Models For Code Infilling Beyond Fixed-size Canvas

2026-02-01 · Zirui Wu, Lin Zheng, Zhihui Xie, Jiacheng Ye 외 arxiv

Diffusion Language Models (DLMs) present a compelling alternative to autoregressive models, offering flexible, any-order infilling without specialized prompting design. However, their practical utility is blocked by a cr…

GLM: General Language Model Pretraining with Autoregressive Blank Infilling

2021-03-18 · ACL 2022 5 · Zhengxiao Du, Yujie Qian, Xiao Liu, Ming Ding 외

There have been various types of pretraining architectures including autoencoding models (e.g., BERT), autoregressive models (e.g., GPT), and encoder-decoder models (e.g., T5). However, none of the pretraining frameworks…

Abstractive Text SummarizationClassificationDecoderDocument Summarization+4

GLM: General Language Model Pretraining with Autoregressive Blank Infilling

2021-11-16 · ACL ARR November 2021 11 · Anonymous

There have been various types of pretraining architectures including autoencoding models (e.g., BERT), autoregressive models (e.g., GPT), and encoder-decoder models (e.g., T5). However, none of the pretraining frameworks…

DecoderLanguage ModelingLanguage ModellingNatural Language Understanding

Flexible-length Text Infilling for Discrete Diffusion Models

2025-06-16 · Andrew Zhang, Anushka Sivakumar, Chiawei Tang, Chris Thomas

Discrete diffusion models are a new class of text generators that offer advantages such as bidirectional context use, parallelizable generation, and flexible prompting compared to autoregressive models. However, a critic…

PositionText Infilling