# SynthTextEval: Synthetic Text Data Generation and Evaluation for High-Stakes Domains

arXiv: https://arxiv.org/abs/2507.07229 · HTML: https://mlsanity.com/paper/2507.07229/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 54 references that are in the map.
- First posted on arXiv 9 Jul 2025.

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

- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers](https://mlsanity.com/paper/2102.01454/) (2021)
- [On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey](https://mlsanity.com/paper/2406.15126/) (2024)
- [The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics](https://mlsanity.com/paper/2102.01672/) (2021)
- [Large Language Models for Data Annotation and Synthesis: A Survey](https://mlsanity.com/paper/2402.13446/) (2024)
- [Numerical Composition of Differential Privacy](https://mlsanity.com/paper/2106.02848/) (2021)
- [Orca 2: Teaching Small Language Models How to Reason](https://mlsanity.com/paper/2311.11045/) (2023)
- [Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe](https://mlsanity.com/paper/2210.14348/) (2022)
- [Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation](https://mlsanity.com/paper/2309.11765/) (2023)
- [The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymization](https://mlsanity.com/paper/2202.00443/) (2022)
- [Rethinking LLM Memorization through the Lens of Adversarial Compression](https://mlsanity.com/paper/2404.15146/) (2024)
- [Synthcity: facilitating innovative use cases of synthetic data in different data modalities](https://mlsanity.com/paper/2301.07573/) (2023)
- [Differentially Private Language Models for Secure Data Sharing](https://mlsanity.com/paper/2210.13918/) (2022)
- [A Customized Text Sanitization Mechanism with Differential Privacy](https://mlsanity.com/paper/2207.01193/) (2022)
- [On the Blind Spots of Model-Based Evaluation Metrics for Text Generation](https://mlsanity.com/paper/2212.10020/) (2022)
- [DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows](https://mlsanity.com/paper/2402.10379/) (2024)
- [PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models](https://mlsanity.com/paper/2311.04044/) (2023)
- [A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage](https://mlsanity.com/paper/2504.21035/) (2025)
- [Auditing and Generating Synthetic Data with Controllable Trust Trade-offs](https://mlsanity.com/paper/2304.10819/) (2023)
- [Evaluating Differentially Private Synthetic Data Generation in High-Stakes Domains](https://mlsanity.com/paper/2410.08327/) (2024)
- [Assessment of Differentially Private Synthetic Data for Utility and Fairness in End-to-End Machine Learning Pipelines for Tabular Data](https://mlsanity.com/paper/2310.19250/) (2023)
- [Mention Annotations Alone Enable Efficient Domain Adaptation for Coreference Resolution](https://mlsanity.com/paper/2210.07602/) (2022)
- [SafeSynthDP: Leveraging Large Language Models for Privacy-Preserving Synthetic Data Generation Using Differential Privacy](https://mlsanity.com/paper/2412.20641/) (2024)
- [Privacy Evaluation Benchmarks for NLP Models](https://mlsanity.com/paper/2409.15868/) (2024)

## Built on by (most cited first, 7 of 7)

- [Controlled Generation for Private Synthetic Text](https://mlsanity.com/paper/2509.25729/) (2025)
- [NodeSynth: Socially Aligned Synthetic Data for AI Evaluation](https://mlsanity.com/paper/2605.14381/) (2026)
- [When Does Synthetic Patent Data Help? Volume-Fidelity Trade-offs in Low-Resource Multi-Label Classification](https://mlsanity.com/paper/2605.24296/) (2026)
- [ROBE: Reversed-Order-Biased-Experts for Extracting Extreme Long-tail Events from Historical Texts](https://mlsanity.com/paper/2608.24268/) (2026)
- [Schematize: An Agentic System for Generating and Refining Information-Extraction Schemas for Legal Research](https://mlsanity.com/paper/2609.22209/) (2026)
- [Beyond Mode Collapse: Generating Diverse Synthetic Expert Conversations via Generative Flow Networks](https://mlsanity.com/paper/2609.38359/) (2026)
- [Synthetic Data Characterization via Training Dynamics](https://mlsanity.com/paper/2609.39447/) (2026)

## Abstract (arXiv)

We present SynthTextEval, a toolkit for conducting comprehensive evaluations of synthetic text. The fluency of large language model (LLM) outputs has made synthetic text potentially viable for numerous applications, such as reducing the risks of privacy violations in the development and deployment of AI systems in high-stakes domains. Realizing this potential, however, requires principled consistent evaluations of synthetic data across multiple dimensions: its utility in downstream systems, the fairness of these systems, the risk of privacy leakage, general distributional differences from the source text, and qualitative feedback from domain experts. SynthTextEval allows users to conduct evaluations along all of these dimensions over synthetic data that they upload or generate using the toolkit's generation module. While our toolkit can be run over any data, we highlight its functionality and effectiveness over datasets from two high-stakes domains: healthcare and law. By consolidating and standardizing evaluation metrics, we aim to improve the viability of synthetic text, and in-turn, privacy-preservation in AI development.