Challenge: Existing studies on text anonymization prioritize privacy preservation at the expense of utility, relying on reference-based metrics like ROUGE, BERTScore, or METEOR to measure textual fidelity.
Approach: They propose an open-source framework for benchmarking text anonymization methods through the lens of privacy and utility task sensitivity.
Outcome: The proposed framework is open-source and provides a Python library, documentation and tutorials.

Similar Papers

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.
Anonymisation Models for Text Data: State of the art, Challenges and Future Directions (2021.acl-long)

Copied to clipboard

Challenge: a paper examines the problem of automated text anonymisation . text anonymization is a prerequisite for secure sharing of documents containing sensitive information about individuals.
Approach: They propose to incorporate explicit measures of disclosure risk into the text anonymisation process to reduce the risk of errors.
Outcome: The proposed approach is based on a case study in which the authors outline the benefits and limitations of the proposed methods.
Multi-Token Completion for Text Anonymization (2026.eacl-long)

Copied to clipboard

Challenge: Text anonymization is a critical task for enabling research and development in high-stakes domains containing private data.
Approach: They propose a method for predicting replacements for sensitive spans with principled use-inspired evaluation criteria.
Outcome: The proposed method produces more realistic text and preserves utility than alternative infilling methods and differentially private mechanisms across multiple domains without retraining.
Adaptive Text Anonymization: Learning Privacy-Utility Trade-offs via Prompt Optimization (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for anonymizing textual documents lack flexibility to adapt to diverse requirements.
Approach: They propose a task formulation in which anonymization strategies are automatically adapted to specific privacy–utility requirements.
Outcome: The proposed framework achieves better privacy–utility trade-off than existing baselines on open-source language models while remaining computationally efficient and effective on larger closed-source models.
NAP2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human (2025.findings-emnlp)

Copied to clipboard

Challenge: a large number of large language models are being used to protect user privacy . sanitizing sensitive text using two common strategies is the answer .
Approach: They propose sanitizing sensitive text using deleting expressions and abstracting them . they propose a tool for text rewriting that uses crowdsourcing and large language models .
Outcome: The proposed approach protects privacy before sending sensitive data to large language models . it combines crowdsourcing and large language modeling to create a text rewrite tool .
Neural Text Sanitization with Explicit Measures of Privacy Risk (2022.aacl-main)

Copied to clipboard

Challenge: Personal data, also known as Personally Identifiable Information (PII), often abound in text documents.
Approach: They propose a method for text sanitization that uses a neural entity recognizer to detect and classify potential personal identifiers and a classifier trained on labelled data to determine which entities to mask .
Outcome: The proposed approach masks all personal identifiers and thereby conceals the identity of the individuals mentioned in the document.
STAMP: Selective Task-Aware Mechanism for Text Privacy (2026.eacl-long)

Copied to clipboard

Challenge: Experimental evaluations on SQuAD, Yelp, and AG News datasets demonstrate that STAMP achieves superior privacy–utility trade-offs across varying per-token privacy budgets.
Approach: They propose a new framework for task-aware text privatization that selectively allocates privacy budgets across tokens by jointly considering (i) each token’s importance to the downstream task and (ii) its privacy sensitivity.
Outcome: The proposed framework achieves superior privacy–utility trade-offs on SQuAD, Yelp, and AG News datasets.
Deep Reinforcement Learning-based Text Anonymization against Private-Attribute Inference (D19-1)

Copied to clipboard

Challenge: Recent research shows textual data alone may contain enough information about users' private-attributes that they do not want to disclose such as age, gender, location, political views and sexual orientation.
Approach: They propose a novel Reinforcement Learning-based Text Anonymizor which extracts a latent representation of the original text w.r.t. a given task and leverages deep reinforcement learning to learn an optimal strategy for manipulating text representations w/ the received privacy and utility feedback.
Outcome: The proposed approach preserves both privacy and utility of textual data while preserving its utility.
INCOGNITUS: A Toolbox for Automated Clinical Notes Anonymization (2023.eacl-demo)

Copied to clipboard

Challenge: a flexible platform for automated text anonymization of clinical notes is presented . the platform guarantees 100% recall by replacing each word with a semantically identical one .
Approach: They propose a platform for automated text anonymization of clinical notes . INCOGNITUS guarantees 100% recall by replacing each word with a semantically identical one .
Outcome: The proposed platform guarantees 100% recall by replacing each word with a semantically identical one.
Keep it Private: Unsupervised Privatization of Online Text (2024.naacl-long)

Copied to clipboard

Challenge: Authorship obfuscation has been evaluated in narrow settings in the NLP literature . superficial edit operations can lead to unnatural outputs, authors say .
Approach: They propose an automatic text privatization framework that fine-tunes a large language model via reinforcement learning to produce rewrites that balance soundness, sense, and privacy.
Outcome: The proposed method maintains high text quality according to automated metrics and human evaluation, and successfully evades several automated authorship attacks.

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