# AI "News" Content Farms Are Easy to Make and Hard to Detect: A Case Study in Italian

arXiv: https://arxiv.org/abs/2406.12128 · HTML: https://mlsanity.com/paper/2406.12128/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 48 references that are in the map.
- First posted on arXiv 17 Jun 2024.

## Builds on (most cited first, 25 of 25)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [Quantifying the Carbon Emissions of Machine Learning](https://mlsanity.com/paper/1910.09700/) (2019)
- [GLTR: Statistical Detection and Visualization of Generated Text](https://mlsanity.com/paper/1906.04043/) (2019)
- [How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection](https://mlsanity.com/paper/2301.07597/) (2023)
- [Can AI-Generated Text be Reliably Detected?](https://mlsanity.com/paper/2303.11156/) (2023)
- [Robust Distortion-free Watermarks for Language Models](https://mlsanity.com/paper/2307.15593/) (2023)
- [Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2401.12070/) (2024)
- [DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2306.05540/) (2023)
- [From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference](https://mlsanity.com/paper/2310.03003/) (2023)
- [Automatic Detection of Machine Generated Text: A Critical Survey](https://mlsanity.com/paper/2011.01314/) (2020)
- [RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors](https://mlsanity.com/paper/2405.07940/) (2024)
- [M4: Multi-generator, Multi-domain, and Multi-lingual Black-Box Machine-Generated Text Detection](https://mlsanity.com/paper/2305.14902/) (2023)
- [On the Possibilities of AI-Generated Text Detection](https://mlsanity.com/paper/2304.04736/) (2023)
- [ChatGPT or Human? Detect and Explain. Explaining Decisions of Machine Learning Model for Detecting Short ChatGPT-generated Text](https://mlsanity.com/paper/2301.13852/) (2023)
- [ArguGPT: evaluating, understanding and identifying argumentative essays generated by GPT models](https://mlsanity.com/paper/2304.07666/) (2023)
- [HowkGPT: Investigating the Detection of ChatGPT-generated University Student Homework through Context-Aware Perplexity Analysis](https://mlsanity.com/paper/2305.18226/) (2023)
- [Differentiate ChatGPT-generated and Human-written Medical Texts](https://mlsanity.com/paper/2304.11567/) (2023)
- [Detecting ChatGPT: A Survey of the State of Detecting ChatGPT-Generated Text](https://mlsanity.com/paper/2309.07689/) (2023)

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

- [People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text](https://mlsanity.com/paper/2501.15654/) (2025)
- [Knowledge Graphs, Large Language Models, and Hallucinations: An NLP Perspective](https://mlsanity.com/paper/2411.14258/) (2024)
- [Beyond Binary: Towards Fine-Grained LLM-Generated Text Detection via Role Recognition and Involvement Measurement](https://mlsanity.com/paper/2410.14259/) (2024)
- [Stress-testing Machine Generated Text Detection: Shifting Language Models Writing Style to Fool Detectors](https://mlsanity.com/paper/2505.24523/) (2025)
- [PhantomHunter: Detecting Unseen Privately-Tuned LLM-Generated Text via Family-Aware Learning](https://mlsanity.com/paper/2506.15683/) (2025)
- [Fact-checking AI-generated news reports: Can LLMs catch their own lies?](https://mlsanity.com/paper/2503.18293/) (2025)
- [Frame In, Frame Out: Measuring Framing Bias in LLM-Generated News Summaries](https://mlsanity.com/paper/2505.05406/) (2025)
- [MultiHal: Multilingual Dataset for Knowledge-Graph Grounded Evaluation of LLM Hallucinations](https://mlsanity.com/paper/2505.14101/) (2025)
- [AI-Associated Lexical Shifts Across 34 Languages: Cross-Lingual Convergence and Diachronic Uptake in News Writing](https://mlsanity.com/paper/2605.25358/) (2026)
- [Local Differences, Global Lessons: Insights from Organisation Policies for International Legislation](https://mlsanity.com/paper/2503.05737/) (2025)
- [LLMs Should Incorporate Explicit Mechanisms for Human Empathy](https://mlsanity.com/paper/2604.10557/) (2026)
- [Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability](https://mlsanity.com/paper/2607.10402/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly used as "content farm" models (CFMs), to generate synthetic text that could pass for real news articles. This is already happening even for languages that do not have high-quality monolingual LLMs. We show that fine-tuning Llama (v1), mostly trained on English, on as little as 40K Italian news articles, is sufficient for producing news-like texts that native speakers of Italian struggle to identify as synthetic. We investigate three LLMs and three methods of detecting synthetic texts (log-likelihood, DetectGPT, and supervised classification), finding that they all perform better than human raters, but they are all impractical in the real world (requiring either access to token likelihood information or a large dataset of CFM texts). We also explore the possibility of creating a proxy CFM: an LLM fine-tuned on a similar dataset to one used by the real "content farm". We find that even a small amount of fine-tuning data suffices for creating a successful detector, but we need to know which base LLM is used, which is a major challenge. Our results suggest that there are currently no practical methods for detecting synthetic news-like texts 'in the wild', while generating them is too easy. We highlight the urgency of more NLP research on this problem.