Re-identification of De-identified Documents with Autoregressive Infilling
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.
Code (0)
등록된 구현이 없습니다.
Tasks
De-identificationRAGSimilar Papers 제목 키워드 기반
Enabling Autoregressive Models to Fill In Masked Tokens
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 ModelingDreamOn: Diffusion Language Models For Code Infilling Beyond Fixed-size Canvas
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
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+4GLM: General Language Model Pretraining with Autoregressive Blank Infilling
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 UnderstandingFlexible-length Text Infilling for Discrete Diffusion Models
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