# To Lie or Not to Lie? Investigating The Biased Spread of Global Lies by LLMs

arXiv: https://arxiv.org/abs/2604.06552 · HTML: https://mlsanity.com/paper/2604.06552/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 35 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Builds on (most cited first, 23 of 23)

- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [Analyzing Leakage of Personally Identifiable Information in Language Models](https://mlsanity.com/paper/2302.00539/) (2023)
- [Are Large Pre-Trained Language Models Leaking Your Personal Information?](https://mlsanity.com/paper/2205.12628/) (2022)
- [Can LLM-Generated Misinformation Be Detected?](https://mlsanity.com/paper/2309.13788/) (2023)
- [On the Risk of Misinformation Pollution with Large Language Models](https://mlsanity.com/paper/2305.13661/) (2023)
- [Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective](https://mlsanity.com/paper/2401.06824/) (2024)
- [DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection](https://mlsanity.com/paper/2402.10426/) (2024)
- [Decoding Echo Chambers: LLM-Powered Simulations Revealing Polarization in Social Networks](https://mlsanity.com/paper/2409.19338/) (2024)
- [Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2411.17713/) (2024)
- [AI-Slop to AI-Polish? Aligning Language Models through Edit-Based Writing Rewards and Test-time Computation](https://mlsanity.com/paper/2504.07532/) (2025)
- [Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixture](https://mlsanity.com/paper/2407.07342/) (2024)
- [Arabic Dataset for LLM Safeguard Evaluation](https://mlsanity.com/paper/2410.17040/) (2024)
- [Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL](https://mlsanity.com/paper/2510.14318/) (2025)
- [Stanceosaurus: Classifying Stance Towards Multilingual Misinformation](https://mlsanity.com/paper/2210.15954/) (2022)
- [Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics](https://mlsanity.com/paper/2501.17273/) (2025)
- [Prompt, Divide, and Conquer: Bypassing Large Language Model Safety Filters via Segmented and Distributed Prompt Processing](https://mlsanity.com/paper/2503.21598/) (2025)
- [Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers](https://mlsanity.com/paper/2501.13302/) (2025)
- [Content Moderation Justice and Fairness on Social Media: Comparisons Across Different Contexts and Platforms](https://mlsanity.com/paper/2403.06034/) (2024)
- [Echo Chambers in the Age of Algorithms: An Audit of Twitter's Friend Recommender System](https://mlsanity.com/paper/2404.06422/) (2024)
- [Stanceosaurus 2.0: Classifying Stance Towards Russian and Spanish Misinformation](https://mlsanity.com/paper/2402.03642/) (2024)
- [Qorgau: Evaluating LLM Safety in Kazakh-Russian Bilingual Contexts](https://mlsanity.com/paper/2502.13640/) (2025)
- [LiteLMGuard: Seamless and Lightweight On-Device Prompt Filtering for Safeguarding Small Language Models against Quantization-induced Risks and Vulnerabilities](https://mlsanity.com/paper/2505.05619/) (2025)
- [An Audit and Analysis of LLM-Assisted Health Misinformation Jailbreaks Against LLMs](https://mlsanity.com/paper/2508.10010/) (2025)

## Abstract (arXiv)

Misinformation is on the rise, and the strong writing capabilities of LLMs lower the barrier for malicious actors to produce and disseminate false information. We study how LLMs behave when prompted to spread misinformation across languages and target countries, and introduce GlobalLies, a multilingual parallel dataset of 440 misinformation generation prompt templates and 6,867 entities, spanning 8 languages and 195 countries. Using both human annotations and large-scale LLM-as-a-judge evaluations across hundreds of thousands of generations from state-of-the-art models, we show that misinformation generation varies systematically based on the country being discussed. Propagation of lies by LLMs is substantially higher in many lower-resource languages and for countries with a lower Human Development Index (HDI). We find that existing mitigation strategies provide uneven protection: input safety classifiers exhibit cross-lingual gaps, and retrieval-augmented fact-checking remains inconsistent across regions due to unequal information availability. We release GlobalLies for research purposes, aiming to support the development of mitigation strategies to reduce the spread of global misinformation: https://github.com/zohaib-khan5040/globallies