arXiv subjects

Dorian Quelle

Publications and source records attributed to Dorian Quelle.

7 recordsLinked to original sources

arXiv2026

InfoOps Bench: A live information operations safety benchmark

In this paper we present an active, constantly updated AI benchmark which measures the integrity of frontier language models against being co-opted for use by authoritarian state "information operations": intentional, coordinated activities by one state to influence public opinion and information ecosystems in another state. These information operations are a well documented, persistent threat against contemporary democracy. Our benchmark is based on real examples from over 2,100 information operations drawn from a live monitoring pipeline which tracks online information assets with links to authoritarian regimes. Alongside this paper, we also release a companion website that updates the benchmark weekly with new claims. The dynamic nature of this public facing benchmark makes it resistant to saturation. In the benchmark, we test 17 models from 8 providers across four prompt framings. We find that most models can be co-opted for information operations at least some of the time. Integrity scores, defined as the share of judged responses in which the model neither preserved nor amplified the claim, range from 9.3% to 91%, an 81.7-percentage-point spread not explained by model size. Models approach participation in information operations in a variety of ways. Some models fabricate details and produce output more harmful than the original input claim; others make claims less harmful even while complying and producing some output. Fact-checking rates vary from 3.2% to 80.8%. Integrity against information operations is at least partly related to refusal to produce content even for benign claims, illustrating the challenge of balancing model usability with safety. Overall, our results show the potential for contemporary information operations to be substantially aided by frontier AI models.

cs.AI↗

arXiv2026

Language Mutations Sustain the Persistences of Conspiracy Theories on Social Media

This study investigates how language mutations affect the persistent diffusion of conspiracy theories on social media. Drawing on a three-year dataset of conspiracy-related posts from X, and applying computational linguistic analysis alongside survival modelling, we find that conspiracy claims with greater semantic mutations have substantially longer lifespans. Mutations in psycholinguistic properties, including pronouns, social reference words, cognitive process terms, risk- and health- related vocabularies, are associated with extended lifespans. Mutations in actor, action and target (AAT) categories are associated with longer lifespans as well. Qualitative analysis identifies two predominant mutation patterns: simplification and assimilation, at both linguistic and AAT structural levels. Taken together, the results advance our understanding of how language mutations contribute to conspiracy persistence online and shed lights on longitudinal content moderation strategies. We argue that content moderation should consider the mutability of conspiracy claims and focus on the core claims that can address their potential variations.

cs.CL↗

arXiv2025

Politics and polarization on Bluesky

Online political discourse is increasingly shaped not by a few dominant platforms but by a fragmented ecosystem of social media spaces, each with its own user base, target audience, and algorithmic mediation of discussion. Such fragmentation may fundamentally change how polarization manifests online. In this study, we investigate the characteristics of political discourse and polarization on the emerging social media site Bluesky. We collect all activity on the platform between December 2024 and May 2025 to map out the platform's political topic landscape and detect distinct polarization patterns. Our comprehensive data collection allows us to employ a data-driven methodology for identifying political themes, classifying user stances, and measuring both structural and content-based polarization across key topics raised in English-language discussions. Our analysis reveals that approximately 13% of Bluesky posts engage with political content, with prominent topics including international conflicts, U.S. politics, and socio-technological debates. We find high levels of structural polarization across several salient political topics. However, the most polarized topics are also highly imbalanced in the numbers of users on opposing sides, with the smaller group consisting of only 1-2% of the users. While discussions in Bluesky echo familiar political narratives and polarization trends, the platform exhibits a more politically homogeneous user base than was typical prior to the current wave of platform fragmentation.

cs.SI↗

arXiv2025

Simple contagion drives population-scale platform migration

Social media platforms mediate professional communication, political expression, and community formation, making the rare instances when users collectively abandon an incumbent platform particularly consequential. Strong network effects raise switching costs and strengthen incumbents' positions, making coordinated exit difficult. Here we link 276,431 scholars on Twitter/X to their respective new profiles among the universe of all 16.7 million Bluesky accounts, tracked from January 2023 to December 2024, using a scalable, high-precision cross-platform matching pipeline. Exploiting exogenous variation from Brazil's court-ordered suspension of Twitter/X and a dynamic matching design, we show that adoption is peer-driven, treatment effects are short-lived and dose-dependent, and contagion is simple, not complex. Three patterns characterize adoption and retention. Adoption concentrates among users deeply embedded in Twitter's social graph. Public political expression predicts migration, consistent with homophilous inflows into a largely left-of-center Bluesky information space. Early reconnection with prior contacts predicts longer tenure and engagement. Our findings provide the first population-scale causal evidence of peer influence in a social media platform migration by exploiting exogenous exposure variation in a natural experiment and using daily dynamic matching. Rather than the complex contagion mechanism often emphasized in the literature, contagion is predominantly simple. Our findings recast migration as a multi-homing strategy that insures against governance uncertainty and show that users who quickly reconnect with prior contacts remain active longer on Bluesky.

cs.SI↗

arXiv2024

Bluesky: Network Topology, Polarization, and Algorithmic Curation

Bluesky is a nascent Twitter-like and decentralized social media network with novel features and unprecedented data access. This paper provides a characterization of its interaction network, studying the political leaning, polarization, network structure, and algorithmic curation mechanisms of five million users. The dataset spans from the website's first release in February of 2023 to May of 2024. We investigate the replies, likes, reposts, and follows layers of the Bluesky network. We find that all networks are characterized by heavy-tailed distributions, high clustering, and short connection paths, similar to other larger social networks. BlueSky introduced feeds-algorithmic content recommenders created for and by users. We analyze all feeds and find that while a large number of custom feeds have been created, users' uptake of them appears to be limited. We analyze the hyperlinks shared by BlueSky's users and find no evidence of polarization in terms of the political leaning of the news sources they share. They share predominantly left-center news sources and little to no links associated with questionable news sources. In contrast to the homogeneous political ideology, we find significant issues-based divergence by studying opinions related to the Israel-Palestine conflict. Two clear homophilic clusters emerge: Pro-Palestinian voices outnumber pro-Israeli users, and the proportion has increased. We conclude by claiming that Bluesky-for all its novel features-is very similar in its network structure to existing and larger social media sites and provides unprecedented research opportunities for social scientists, network scientists, and political scientists alike.

cs.SI↗

arXiv2023

Lost in translation: using global fact-checks to measure multilingual misinformation prevalence, spread, and evolution

Misinformation and disinformation are growing threats in the digital age, affecting people across languages and borders. However, no research has investigated the prevalence of multilingual misinformation and quantified the extent to which misinformation diffuses across languages. This paper investigates the prevalence and dynamics of multilingual misinformation through an analysis of 264,487 fact-checks spanning 95 languages. To study the evolution of claims over time and mutations across languages, we represent fact-checks with multilingual sentence embeddings and build a graph where semantically similar claims are linked. We provide quantitative evidence of repeated fact-checking efforts and establish that claims diffuse across languages. Specifically, we find that while the majority of misinformation claims are only fact-checked once, 10.26%, corresponding to more than 27,000 claims, are checked multiple times. Using fact-checks as a proxy for the spread of misinformation, we find 32.26% of repeated claims cross linguistic boundaries, suggesting that some misinformation permeates language barriers. However, spreading patterns exhibit strong assortativity, with misinformation more likely to spread within the same language or language family. Next we show that fact-checkers take more time to fact-check claims that have crossed language barriers and model the temporal and cross-lingual evolution of claims. We analyze connected components and shortest paths connecting different versions of a claim finding that claims gradually drift over time and undergo greater alteration when traversing languages. Misinformation changes over time, reducing the effectiveness of static claim matching algorithms. The findings advocate for expanded information sharing between fact-checkers globally while underscoring the importance of localized verification.

cs.CL↗

arXiv2023

The Perils & Promises of Fact-checking with Large Language Models

Automated fact-checking, using machine learning to verify claims, has grown vital as misinformation spreads beyond human fact-checking capacity. Large Language Models (LLMs) like GPT-4 are increasingly trusted to write academic papers, lawsuits, and news articles and to verify information, emphasizing their role in discerning truth from falsehood and the importance of being able to verify their outputs. Understanding the capacities and limitations of LLMs in fact-checking tasks is therefore essential for ensuring the health of our information ecosystem. Here, we evaluate the use of LLM agents in fact-checking by having them phrase queries, retrieve contextual data, and make decisions. Importantly, in our framework, agents explain their reasoning and cite the relevant sources from the retrieved context. Our results show the enhanced prowess of LLMs when equipped with contextual information. GPT-4 outperforms GPT-3, but accuracy varies based on query language and claim veracity. While LLMs show promise in fact-checking, caution is essential due to inconsistent accuracy. Our investigation calls for further research, fostering a deeper comprehension of when agents succeed and when they fail.

cs.CL↗