# Privacy-Preserving Domain Adaptation of Semantic Parsers

arXiv: https://arxiv.org/abs/2212.10520 · HTML: https://mlsanity.com/paper/2212.10520/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 58 references that are in the map.
- First posted on arXiv 20 Dec 2022.

## Builds on (most cited first, 30 of 41)

- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers](https://mlsanity.com/paper/2102.01454/) (2021)
- [Does Learning Require Memorization? A Short Tale about a Long Tail](https://mlsanity.com/paper/1906.05271/) (2019)
- [Large Language Models Can Be Strong Differentially Private Learners](https://mlsanity.com/paper/2110.05679/) (2021)
- [Differentially Private Fine-tuning of Language Models](https://mlsanity.com/paper/2110.06500/) (2021)
- [The Composition Theorem for Differential Privacy](https://mlsanity.com/paper/1311.0776/) (2013)
- [Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models](https://mlsanity.com/paper/2205.10770/) (2022)
- [What Does it Mean for a Language Model to Preserve Privacy?](https://mlsanity.com/paper/2202.05520/) (2022)
- [Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks](https://mlsanity.com/paper/2203.03929/) (2022)
- [Task-Oriented Dialogue as Dataflow Synthesis](https://mlsanity.com/paper/2009.11423/) (2020)
- [Large-Scale Differentially Private BERT](https://mlsanity.com/paper/2108.01624/) (2021)
- [Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe](https://mlsanity.com/paper/2210.14348/) (2022)
- [Semantic Parsing for Task Oriented Dialog using Hierarchical Representations](https://mlsanity.com/paper/1810.07942/) (2018)
- [On the Generalization Benefit of Noise in Stochastic Gradient Descent](https://mlsanity.com/paper/2006.15081/) (2020)
- [Grounded Adaptation for Zero-shot Executable Semantic Parsing](https://mlsanity.com/paper/2009.07396/) (2020)
- [Differentially Private Language Models for Secure Data Sharing](https://mlsanity.com/paper/2210.13918/) (2022)
- [Selective Differential Privacy for Language Modeling](https://mlsanity.com/paper/2108.12944/) (2021)
- [Enabling Fast Differentially Private SGD via Just-in-Time Compilation and Vectorization](https://mlsanity.com/paper/2010.09063/) (2020)
- [Differentially Private Language Models Benefit from Public Pre-training](https://mlsanity.com/paper/2009.05886/) (2020)
- [Model-based Interactive Semantic Parsing: A Unified Framework and A Text-to-SQL Case Study](https://mlsanity.com/paper/1910.05389/) (2019)
- [Conversational Semantic Parsing for Dialog State Tracking](https://mlsanity.com/paper/2010.12770/) (2020)
- [Transferable Dialogue Systems and User Simulators](https://mlsanity.com/paper/2107.11904/) (2021)
- [Submix: Practical Private Prediction for Large-Scale Language Models](https://mlsanity.com/paper/2201.00971/) (2022)
- [An Imitation Game for Learning Semantic Parsers from User Interaction](https://mlsanity.com/paper/2005.00689/) (2020)
- [Learning Adaptive Language Interfaces through Decomposition](https://mlsanity.com/paper/2010.05190/) (2020)
- [Controlled Text Generation for Data Augmentation in Intelligent Artificial Agents](https://mlsanity.com/paper/1910.03487/) (2019)

## Built on by (most cited first, 12 of 12)

- [Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation](https://mlsanity.com/paper/2309.11765/) (2023)
- [Trust No Bot: Discovering Personal Disclosures in Human-LLM Conversations in the Wild](https://mlsanity.com/paper/2407.11438/) (2024)
- [CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation](https://mlsanity.com/paper/2407.07087/) (2024)
- [ALFA: Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoning](https://mlsanity.com/paper/2502.14860/) (2025)
- [Differentially Private Natural Language Models: Recent Advances and Future Directions](https://mlsanity.com/paper/2301.09112/) (2023)
- [A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage](https://mlsanity.com/paper/2504.21035/) (2025)
- [Synthetic Query Generation for Privacy-Preserving Deep Retrieval Systems using Differentially Private Language Models](https://mlsanity.com/paper/2305.05973/) (2023)
- [Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning](https://mlsanity.com/paper/2410.12085/) (2024)
- [Utility Theory of Synthetic Data Generation](https://mlsanity.com/paper/2305.10015/) (2023)
- [Differentially Private Learning Needs Better Model Initialization and Self-Distillation](https://mlsanity.com/paper/2410.17566/) (2024)
- [LatticeGen: A Cooperative Framework which Hides Generated Text in a Lattice for Privacy-Aware Generation on Cloud](https://mlsanity.com/paper/2309.17157/) (2023)
- [Differentially Private Preference Data Synthesis for Large Language Model Alignment](https://mlsanity.com/paper/2605.30808/) (2026)

## Abstract (arXiv)

Task-oriented dialogue systems often assist users with personal or confidential matters. For this reason, the developers of such a system are generally prohibited from observing actual usage. So how can they know where the system is failing and needs more training data or new functionality? In this work, we study ways in which realistic user utterances can be generated synthetically, to help increase the linguistic and functional coverage of the system, without compromising the privacy of actual users. To this end, we propose a two-stage Differentially Private (DP) generation method which first generates latent semantic parses, and then generates utterances based on the parses. Our proposed approach improves MAUVE by 2.5× and parse tree function type overlap by 1.3× relative to current approaches for private synthetic data generation, improving both on fluency and semantic coverage. We further validate our approach on a realistic domain adaptation task of adding new functionality from private user data to a semantic parser, and show overall gains of 8.5% points in accuracy with the new feature.