Fake News Detectors are Biased against Texts Generated by Large Language Models
cs.CL, cs.AI
Submitted: 2023-09-15
Updated: 2026-11-13
Comments: The first two authors contributed equally
License: http://creativecommons.org/licenses/by/4.0/
The gist: The spread of fake news has emerged as a critical challenge, undermining trust and posing threats to society.
Terminology
Abstract
The spread of fake news has emerged as a critical challenge, undermining trust and posing threats to society. In the era of Large Language Models (LLMs), the capability to generate believable fake content has intensified these concerns. In this study, we present a novel paradigm to evaluate fake news detectors in scenarios involving both human-written and LLM-generated misinformation. Intriguingly, our findings reveal a significant bias in many existing detectors: they are more prone to flagging LLM-generated content as fake news while often misclassifying human-written fake news as genuine. This unexpected bias appears to arise from distinct linguistic patterns inherent to LLM outputs. To address this, we introduce a mitigation strategy that leverages adversarial training with LLM-paraphrased genuine news. The resulting model yielded marked improvements in detection accuracy for both human and LLM-generated news. To further catalyze research in this domain, we release two comprehensive datasets, GossipCop++ and PolitiFact++, thus amalgamating human-validated articles with LLM-generated fake and real news.
Sources
- Recent Advances in Adversarial Training for Adversarial Robustness
- Machine-Made Media: Monitoring the Mobilization of Machine-Generated Articles on Misinformation and Mainstream News Websites
- Faking Fake News for Real Fake News Detection: Propaganda-loaded Training Data Generation
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
- StarCoder: may the source be with you!
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
- On the Risk of Misinformation Pollution with Large Language Models
- DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text
- LLaMA: Open and Efficient Foundation Language Models
- Ethical and social risks of harm from Language Models
- Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity
- Source Code Data Augmentation for Deep Learning: A Survey
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data