arXiv AI
Jul 17
Pretraining Data Can Be Poisoned through Computational Propaganda
arXiv:2607. 15267v1 Announce Type: new Abstract: Poisoning pretraining data can introduce harmful behaviors to LMs that are difficult to detect and mitigate.
Forecasting potential misuses of language models for disinformation campaigns and how to reduce risk
OpenAI researchers collaborated with Georgetown University’s Center for Security and Emerging Technology and the Stanford Internet Observatory to investigate how large language models might be misused for disinformation purposes. The collaboration included an October 2021 workshop bringing together 30 disinformation researchers, machine learning experts, and policy analysts, and culminated in a co-authored report building on more than a year of research.
Related stories
arXiv Machine Learning
5d ago
Fake News Theories: Harnessing Disciplinary Insights for Computational Modeling, Detection, and Explanation
The paper presents a theory-informed computational framework that converts cross-disciplinary theories of fake news into measurable features for automated detection and explanation. By reviewing theories from social sciences, psychology, economics, and more, the authors establish a broad theoretical foundation for computational modeling. Experiments on benchmark datasets demonstrate that theory-derived features are predictive, provide interpretable diagnostic signals, and that multi-feature models generally outperform individual features, though gains are modest.
arXiv Computation and Language
Sep 21
From Generation to Detection: Exploration of Discourse Driven Scenario based LLM Generated Fake News
arXiv:2609.20838v1 Announce Type: new Abstract: In this study, we examine how modern LLMs generate and detect fake news under controlled settings across four manipulation scenarios. These are open-en...
arXiv AI
Jul 15
Evaluating Health Misinformation in Low-Resource Languages: Integrating Small Language Models with a Culturally-Sensitive Responsible NLP Framework (Bangla as a Case Study)
arXiv:2607. 12336v1 Announce Type: cross Abstract: Artificial Intelligence (AI) technologies, while serving as a foundational enabler for modern social media and digital health services, exert a bivalent effect by simultaneously acting as a combatant against and a spread vector for misinformation.
arXiv AI
Sep 15
Data Security in Large Language Models: Risks, Defense, and Directions
arXiv:2508.02312v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs), now a foundation in advancing natural language processing, power applications such as text generation, machine...
arXiv AI
Aug 11
Build it, Break it, Repeat: Benchmarking and improving LLM-manipulated disinformation detection in social media posts
arXiv:2608. 09510v1 Announce Type: cross Abstract: Detecting machine-generated disinformation on social media is increasingly difficult as large language models (LLMs) make it easier to generate and rewrite misleading content at scale.
arXiv AI
Aug 18
Propaganda Forensics: Recovering the Generation Pipeline of an AI-Driven Influence Campaign
arXiv:2608. 15746v1 Announce Type: new Abstract: We present a forensic analysis of the generation pipeline behind a recent AI-driven influence campaign.
arXiv AI
Jul 17
Transcoders for Investigating Deception in Language Models
arXiv:2607. 14791v1 Announce Type: new Abstract: Transcoders have recently emerged as a promising approach for mechanistic interpretability (MI), enabling circuit-level analysis of model behaviour.
arXiv AI
Jun 9
Auditing Proprietary Alignment in Large Language Models: A Comparative Framework Without a Ground-Truth Standard
arXiv:2606. 08381v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly released and deployed through opaque development and deployment pipelines, enabling model providers to inject intentional, provider-specific policies without officially announcing them.
arXiv AI
Jul 14
Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability
arXiv:2607. 10402v1 Announce Type: cross Abstract: Large language models (LLMs) have transformed misinformation from a primarily content-centric problem into a broader ecosystem-level security challenge.
arXiv Computation and Language
Aug 25
No One Model Catches Every Harm: Benchmarking Content Moderation Across Safety Scenarios
arXiv:2608.21775v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in real-world applications, yet they remain vulnerable to generating harmful content. From adver...
arXiv Machine Learning
Sep 3
GPTBIAS: A Comprehensive Framework for Evaluating Bias in Large Language Models
The paper introduces GPTBIAS, a framework that uses powerful large language models like GPT‑4 to evaluate bias in other LLMs. It employs specially crafted prompts called Bias Attack Instructions to probe for bias and outputs a bias score along with detailed information such as bias types, affected demographics, keywords, reasons, and improvement suggestions. Extensive experiments demonstrate the framework’s effectiveness and usability.