mlsanityData to 7 Oct 2026

Thinking Outside of the Differential Privacy Box: A Case Study in Text Privatization with Language Model Prompting

arXiv 2410.00751 ↗First posted 1 Oct 2024cs.CLcited by 11

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

The field of privacy-preserving Natural Language Processing has risen in popularity, particularly at a time when concerns about privacy grow with the proliferation of Large Language Models. One solution consistently appearing in recent literature has been the integration of Differential Privacy (DP) into NLP techniques. In this paper, we take these approaches into critical view, discussing the restrictions that DP integration imposes, as well as bring to light the challenges that such restrictions entail. To accomplish this, we focus on DP-Prompt, a recent method for text privatization leveraging language models to rewrite texts. In particular, we explore this rewriting task in multiple scenarios, both with DP and without DP. To drive the discussion on the merits of DP in NLP, we conduct empirical utility and privacy experiments. Our results demonstrate the need for more discussion on the usability of DP in NLP and its benefits over non-DP approaches.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 4 of its 36 references that are in the map. First posted on arXiv 1 Oct 2024.

Builds on

4 of 36 references.

References · 4

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  2. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  3. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,219
  4. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 705

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 7; 2026: 4.

11 papers.

  1. 2025LLM-as-a-Judge for Privacy Evaluation? Exploring the Alignment of Human and LLM Perceptions of Privacy in Textual Datacited by 10
  2. 2025On the Impact of Noise in Differentially Private Text Rewritingcited by 8
  3. 2025Spend Your Budget Wisely: Towards an Intelligent Distribution of the Privacy Budget in Differentially Private Text Rewritingcited by 5
  4. 2025How do we measure privacy in text? A survey of text anonymization metricscited by 5
  5. 2025Leveraging Semantic Triples for Private Document Generation with Local Differential Privacy Guaranteescited by 3
  6. 2026STAMP: Selective Task-Aware Mechanism for Text Privacycited by 2
  7. 2025Investigating User Perspectives on Differentially Private Text Privatizationcited by 1
  8. 2025With Privacy, Size Matters: On the Importance of Dataset Size in Differentially Private Text Rewritingcited by 0
  9. 2026The Conundrum of Trustworthy Research on Attacking Personally Identifiable Information Removal Techniquescited by 0
  10. 2026PrivBench: A Holistic and Modular Benchmarking Platform for Evaluating Text-to-Text Privatizationcited by 0
  11. 2026I Am No One: Style-Aware Paraphrasing for Text Anonymizationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models
  2. 2025Controlling What You Share: Assessing Language Model Adherence to Privacy Preferences
  3. 2023InferDPT: Privacy-Preserving Inference for Closed-box Large Language Model
  4. 2024Differentially Private Training of Mixture of Experts Models
  5. 2025Improved Algorithms for Differentially Private Language Model Alignment
  6. 2024Evaluating Differentially Private Synthetic Data Generation in High-Stakes Domains
  7. 2026Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation
  8. 2025Synthesizing Privacy-Preserving Text Data via Finetuning without Finetuning Billion-Scale LLMs