# Fact-Enhanced Synthetic News Generation

arXiv: https://arxiv.org/abs/2012.04778 · HTML: https://mlsanity.com/paper/2012.04778/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Dec 2020.

## Built on by (most cited first, 22 of 22)

- [Can LLM-Generated Misinformation Be Detected?](https://mlsanity.com/paper/2309.13788/) (2023)
- [TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation](https://mlsanity.com/paper/2109.13296/) (2021)
- [Stylometric Detection of AI-Generated Text in Twitter Timelines](https://mlsanity.com/paper/2303.03697/) (2023)
- [Tracing Text Provenance via Context-Aware Lexical Substitution](https://mlsanity.com/paper/2112.07873/) (2021)
- [Faking Fake News for Real Fake News Detection: Propaganda-loaded Training Data Generation](https://mlsanity.com/paper/2203.05386/) (2022)
- [Fake News Detectors are Biased against Texts Generated by Large Language Models](https://mlsanity.com/paper/2309.08674/) (2023)
- [FakeGPT: Fake News Generation, Explanation and Detection of Large Language Models](https://mlsanity.com/paper/2310.05046/) (2023)
- [Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systems](https://mlsanity.com/paper/2209.03755/) (2022)
- [SciNews: From Scholarly Complexities to Public Narratives -- A Dataset for Scientific News Report Generation](https://mlsanity.com/paper/2403.17768/) (2024)
- [Real-time Factuality Assessment from Adversarial Feedback](https://mlsanity.com/paper/2410.14651/) (2024)
- [When Autonomy Goes Rogue: Preparing for Risks of Multi-Agent Collusion in Social Systems](https://mlsanity.com/paper/2507.14660/) (2025)
- [Stochastic Parrots Looking for Stochastic Parrots: LLMs are Easy to Fine-Tune and Hard to Detect with other LLMs](https://mlsanity.com/paper/2304.08968/) (2023)
- [Summarization, Simplification, and Generation: The Case of Patents](https://mlsanity.com/paper/2104.14860/) (2021)
- [Integrating Human-in-the-loop into Swarm Learning for Decentralized Fake News Detection](https://mlsanity.com/paper/2201.02048/) (2022)
- [A Symbolic Adversarial Learning Framework for Evolving Fake News Generation and Detection](https://mlsanity.com/paper/2508.19633/) (2025)
- [Style-News: Incorporating Stylized News Generation and Adversarial Verification for Neural Fake News Detection](https://mlsanity.com/paper/2401.15509/) (2024)
- [Holdout-Based Fidelity and Privacy Assessment of Mixed-Type Synthetic Data](https://mlsanity.com/paper/2104.00635/) (2021)
- [Emotion Conditioned Creative Dialog Generation](https://mlsanity.com/paper/2212.02907/) (2022)
- [Crafting Tomorrow's Headlines: Neural News Generation and Detection in English, Turkish, Hungarian, and Persian](https://mlsanity.com/paper/2408.10724/) (2024)
- [Collocation2Text: Controllable Text Generation from Guide Phrases in Russian](https://mlsanity.com/paper/2206.09248/) (2022)
- [Coincidental Generation](https://mlsanity.com/paper/2304.01108/) (2023)
- [AI-Generated Lecture Slides for Improving Slide Element Detection and Retrieval](https://mlsanity.com/paper/2506.23605/) (2025)

## Abstract (arXiv)

The advanced text generation methods have witnessed great success in text summarization, language translation, and synthetic news generation. However, these techniques can be abused to generate disinformation and fake news. To better understand the potential threats of synthetic news, we develop a new generation method FactGen to generate high-quality news content. The existing text generation methods either afford limited supplementary information or lose consistency between the input and output which makes the synthetic news less trustworthy. To address these issues, FactGen retrieves external facts to enrich the output and reconstructs the input claim from the generated content to improve the consistency among the input and the output. Experiment results on real-world datasets show that the generated news contents of FactGen are consistent and contain rich facts. We also discuss the possible defending method to identify these synthetic news pieces if FactGen is used to generate synthetic news.