Challenge: Neural Networks (NNs) are used to model large amounts of data, such as text data, and have shown to be very useful for language modelling.
Approach: They propose to use a Dutch language model for hospital notes to anonymize a model trained on large amounts of data and publish it online.
Outcome: The proposed method predicts a name-like token 0.2% of the time, compared to the original training data.

Similar Papers

Adapting Language Models When Training on Privacy-Transformed Data (2022.lrec-1)

Copied to clipboard

Challenge: Using data sanitization methods to remove personal information from spoken messages is not effective because privacy-transformed data is unlikely to match the test distribution.
Approach: They propose to use a data sanitization approach to remove personal information from spoken messages by replacing named entities with other words from the same class.
Outcome: The proposed approach removes personal information from the spoken messages using an automatic named entity recognition method.
Bootstrapping Text Anonymization Models with Distant Supervision (2022.lrec-1)

Copied to clipboard

Challenge: Personal data is ubiquitous in text documents.
Approach: They propose a method to bootstrap text anonymization models based on distant supervision by using a knowledge graph to annotate text documents including personal data.
Outcome: The proposed method uses a knowledge graph to annotate text documents including personal data about a subset of individuals.
Data-Constrained Synthesis of Training Data for De-Identification (2025.acl-long)

Copied to clipboard

Challenge: sensitive domains lack widely available datasets due to privacy risks . recent studies have focused on evaluating the privacy of the synthetic text .
Approach: They domain-adapt LLMs to clinical domain and generate synthetic clinical texts . they then generate NER models that can be annotated with tags for PII .
Outcome: The proposed model performs better than the original model using smaller datasets.
Generating Synthetic Free-text Medical Records with Low Re-identification Risk using Masked Language Modeling (2025.naacl-srw)

Copied to clipboard

Challenge: Existing methods to generate medical records using Causal Language Modelling are limited due to privacy concerns.
Approach: They propose a method for generating medical records using Masked Language Modelling using Causal language models.
Outcome: The proposed method produces high-quality synthetic data with a re-identification risk of only 3.5% and a patient recall of 96%.
TAG: Gradient Attack on Transformer-based Language Models (2021.findings-emnlp)

Copied to clipboard

Challenge: Recent studies show that publicly shared gradients in the training process can reveal the private training data to a third-party.
Approach: They propose a gradient attack algorithm to reconstruct the local training data using GLUE benchmarks.
Outcome: The proposed algorithm achieves 1.5x recover rate and 2.5x ROUGE-2 over previous methods without the need of ground truth label.
DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Existing studies have demonstrated that pretrained language models memorize and regurgitate a significant portion of training data, including atypical data points that appear only once in the training data.
Approach: They propose a method to locate and erase risky neurons in order to eliminate the impact of privacy data in the model in batches.
Outcome: The proposed method eliminates the impact of privacy data in the model in batches without affecting the model's performance.
Robust Utility-Preserving Text Anonymization Based on Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing techniques face challenges of re-identification ability of large language models . anonymizing text that contains sensitive information is crucial for a wide range of applications .
Approach: They propose a framework that integrates three key LLM components to perform anonymization.
Outcome: The proposed model outperforms baselines while maintaining greater data utility in downstream tasks.
Sensitive Data Detection and Classification in Spanish Clinical Text: Experiments with BERT (2020.lrec-1)

Copied to clipboard

Challenge: Massive digital data processing can endanger personal data privacy . anonymisation involves removing or replacing sensitive information from data .
Approach: They propose to use a BERT-based sequence labelling model to conduct an experiment on clinical datasets in Spanish.
Outcome: The proposed model outperforms existing models on clinical datasets in Spanish and shows that it is highly competitive with other models.
Adversarial Learning of Privacy-Preserving Text Representations for De-Identification of Medical Records (P19-1)

Copied to clipboard

Challenge: De-identification is the task of detecting protected health information (PHI) in medical text.
Approach: They propose to create shareable representations of medical text that contain no PHI and can be shared between organizations to create unified datasets for training de-identification models.
Outcome: The proposed representation allows training a simple LSTM-CRF model to an F1 score of 97.4%.
Why Generate When You Can Discriminate? A Novel Technique for Text Classification using Language Models (2024.findings-eacl)

Copied to clipboard

Challenge: Existing methods for text classification using autoregressive language models are limited . authors propose a novel technique for text classification using autoreregressives .
Approach: They propose a two-step technique for text classification using autoregressive language models . they use a set of perplexity and log-likelihood based numeric features to elicit a text instance .
Outcome: The proposed technique eliminates parameter updates in LMs and does not limit training examples . it is evaluated across 5 datasets and compares with multiple competent baselines .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations