Kellin Pelrine

Matthew Kowal

Antonio A. Arechar

Adam Gleave

David G. Rand

Gordon Pennycook

Large language models (LLMs) have been shown to be persuasive across a variety of contexts. But it remains unclear whether this persuasive p… (see more)ower advantages truth over falsehood, or if LLMs can promote misbeliefs just as easily as refuting them. Here, we investigate this question across three pre-registered experiments in which participants (N = 2,724 Americans) discussed a conspiracy theory they were uncertain about with GPT-4o, and the model was instructed to either argue against ("debunking") or for ("bunking") that conspiracy. When using a"jailbroken"GPT-4o variant with guardrails removed, the AI was as effective at increasing conspiracy belief as decreasing it. Concerningly, the bunking AI was rated more positively, and increased trust in AI, more than the debunking AI. Surprisingly, we found that using standard GPT-4o produced very similar effects, such that the guardrails imposed by OpenAI did little to prevent the LLM from promoting conspiracy beliefs. Encouragingly, however, a corrective conversation reversed these newly induced conspiracy beliefs, and simply prompting GPT-4o to only use accurate information dramatically reduced its ability to increase conspiracy beliefs. Our findings demonstrate that LLMs possess potent abilities to promote both truth and falsehood, but that potential solutions may exist to help mitigate this risk.

2026-01-07

ArXiv (preprint)

$\texttt{BluePrint}$: A Social Media User Dataset for LLM Persona Evaluation and Training

Aur'elien Buck-Kaeffer

Je Qin Chooi

Dan Zhao

Zachary Yang

Large language models (LLMs) offer promising capabilities for simulating social media dynamics at scale, enabling studies that would be ethi… (see more)cally or logistically challenging with human subjects. However, the field lacks standardized data resources for fine-tuning and evaluating LLMs as realistic social media agents. We address this gap by introducing SIMPACT, the SIMulation-oriented Persona and Action Capture Toolkit, a privacy respecting framework for constructing behaviorally-grounded social media datasets suitable for training agent models. We formulate next-action prediction as a task for training and evaluating LLM-based agents and introduce metrics at both the cluster and population levels to assess behavioral fidelity and stylistic realism. As a concrete implementation, we release BluePrint, a large-scale dataset built from public Bluesky data focused on political discourse. BluePrint clusters anonymized users into personas of aggregated behaviours, capturing authentic engagement patterns while safeguarding privacy through pseudonymization and removal of personally identifiable information. The dataset includes a sizable action set of 12 social media interaction types (likes, replies, reposts, etc.), each instance tied to the posting activity preceding it. This supports the development of agents that use context-dependence, not only in the language, but also in the interaction behaviours of social media to model social media users. By standardizing data and evaluation protocols, SIMPACT provides a foundation for advancing rigorous, ethically responsible social media simulations. BluePrint serves as both an evaluation benchmark for political discourse modeling and a template for building domain specific datasets to study challenges such as misinformation and polarization.

2025-09-26

ArXiv (preprint)

CrediBench: Building Web-Scale Network Datasets for Information Integrity

James Zhou

Michael M. Bronstein

Shenyang Huang

Online misinformation poses an escalating threat, amplified by the Internet's open nature and increasingly capable LLMs that generate persua… (see more)sive yet deceptive content. Existing misinformation detection methods typically focus on either textual content or network structure in isolation, failing to leverage the rich, dynamic interplay between website content and hyperlink relationships that characterizes real-world misinformation ecosystems. We introduce CrediBench: a large-scale data processing pipeline for constructing temporal web graphs that jointly model textual content and hyperlink structure for misinformation detection. Unlike prior work, our approach captures the dynamic evolution of general misinformation domains, including changes in both content and inter-site references over time. Our processed one-month snapshot extracted from the Common Crawl archive in December 2024 contains 45 million nodes and 1 billion edges, representing the largest web graph dataset made publicly available for misinformation research to date. From our experiments on this graph snapshot, we demonstrate the strength of both structural and webpage content signals for learning credibility scores, which measure source reliability. The pipeline and experimentation code are all available here, and the dataset is in this folder.

2025-09-21

NPGML @ Neural Information Processing Systems (poster)

SandboxSocial: A Sandbox for Social Media Using Multimodal AI Agents

Sneheel Sarangi

Gayatri Krishnakumar

Busra Tugce Gurbuz

Austin Welch

Zachary Yang

Andreea Musulan

Hao Yu

Ethan Kosak-Hine

Tom Gibbs

Camille Thibault

Dan Zhao

The online information ecosystem enables influence campaigns of unprecedented scale and impact. We urgently need empirically grounded approa… (see more)ches to counter the growing threat of malicious campaigns, now amplified by generative AI. But, developing defenses in real-world settings is impractical. Social system simulations with agents modelled using Large Language Models (LLMs) are a promising alternative approach and a growing area of research. However, existing simulators lack features needed to capture the complex information-sharing dynamics of platform-based social networks. To bridge this gap, we present SandboxSocial, a new simulator that includes several key innovations, mainly: (1) a virtual social media platform (modelled as Mastodon and mirrored in an actual Mastodon server) that enables a realistic setting in which agents interact; (2) an adapter that uses real-world user data to create more grounded agents and social media content; and (3) multi-modal capabilities that enable our agents to interact using both text and images---just as humans do on social media. We make the simulator more useful to researchers by providing measurement and analysis tools that track simulation dynamics and compute evaluation metrics to compare experimental results.

2025-08-15

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence (published)

Veracity: An Open-Source AI Fact-Checking System

Taylor Lynn Curtis

William Garneau

Manon Gruaz

Mike Pinder

Li Wei Wang

Sukanya Krishna

Luda Cohen

The proliferation of misinformation poses a significant threat to society, exacerbated by the capabilities of generative AI. This demo paper… (see more) introduces Veracity, an open-source AI system designed to empower individuals to combat misinformation through transparent and accessible fact-checking. Veracity leverages the synergy between Large Language Models (LLMs) and web retrieval agents to analyze user-submitted claims and provide grounded veracity assessments with intuitive explanations. Key features include multilingual support, numerical scoring of claim veracity, and an interactive interface inspired by familiar messaging applications. This paper will showcase Veracity's ability to not only detect misinformation but also explain its reasoning, fostering media literacy and promoting a more informed society.

2025-08-15

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence (published)

TRUTH: Teaching LLMs to Rerank for Truth in Misinformation Detection

Hao Yu

Shenyang Huang

Zachary Yang

2025-07-24

colmweb.org/COLM/2025/Workshop/SoLaR (poster)

It's the Thought that Counts: Evaluating the Attempts of Frontier LLMs to Persuade on Harmful Topics

Matthew Kowal

Jasper Timm

Thomas H Costello

Antonio A. Arechar

Gordon Pennycook

David G. Rand

Adam Gleave

Persuasion is a powerful capability of large language models (LLMs) that both enables beneficial applications (e.g. helping people quit smok… (see more)ing) and raises significant risks (e.g. large-scale, targeted political manipulation). Prior work has found models possess a significant and growing persuasive capability, measured by belief changes in simulated or real users. However, these benchmarks overlook a crucial risk factor: the propensity of a model to attempt to persuade in harmful contexts. Understanding whether a model will blindly ``follow orders'' to persuade on harmful topics (e.g. glorifying joining a terrorist group) is key to understanding the efficacy of safety guardrails. Moreover, understanding if and when a model will engage in persuasive behavior in pursuit of some goal is essential to understanding the risks from agentic AI systems. We propose the Attempt to Persuade Eval (APE) benchmark, that shifts the focus from persuasion success to persuasion attempts, operationalized as a model's willingness to generate content aimed at shaping beliefs or behavior. Our evaluation framework probes frontier LLMs using a multi-turn conversational setup between simulated persuader and persuadee agents. APE explores a diverse spectrum of topics including conspiracies, controversial issues, and non-controversially harmful content. We introduce an automated evaluator model to identify willingness to persuade and measure the frequency and context of persuasive attempts. We find that many open and closed-weight models are frequently willing to attempt persuasion on harmful topics and that jailbreaking can increase willingness to engage in such behavior. Our results highlight gaps in current safety guardrails and underscore the importance of evaluating willingness to persuade as a key dimension of LLM risk. APE is available at github.com/AlignmentResearch/AttemptPersuadeEval

2025-05-31

arXiv (published)

From Intuition to Understanding: Using AI Peers to Overcome Physics Misconceptions

Ruben Weijers

Denton Wu

Hannah Betts

Tamara Jacod

Yuxiang Guan

Vidya Sujaya

Kushal Dev

Toshali Goel

William Delooze

Ying Wu

Generative AI has the potential to transform personalization and accessibility of education. However, it raises serious concerns about accur… (see more)acy and helping students become independent critical thinkers. In this study, we designed a helpful yet fallible AI "Peer" to help students correct fundamental physics misconceptions related to Newtonian mechanic concepts. In contrast to approaches that seek near-perfect accuracy to create an authoritative AI tutor or teacher, we directly inform students that this AI can answer up to 40\% of questions incorrectly. In a randomized controlled trial with 165 students, those who engaged in targeted dialogue with the AI Peer achieved post-test scores that were, on average, 10.5 percentage points higher—with over 20 percentage points higher normalized gain—than a control group that discussed physics history. Qualitative feedback indicated that 91% of the treatment group's AI interactions were rated as helpful. Furthermore, by comparing student performance on pre- and post-test questions about the same concept, along with experts' annotations of the AI interactions, we find initial evidence suggesting the improvement in performance does not depend on the correctness of the AI. With further research, the AI Peer paradigm described here could open new possibilities for how we learn, adapt to, and grow with AI.

2025-03-04

ICLR.cc/2025/Workshop/Bi-Align (poster)

Rethinking Anti-Misinformation AI

This paper takes a position on how anti-misinformation AI works should be developed for the online misinformation context. We observe that t… (see more)he current literature is dominated by works that produce more information for users to process and that this function faces various challenges in bringing meaningful effects to reality. We use anti-misinformation insights from other domains to suggest a redirection of the existing line of work and identify an under-explored opportunity AI can facilitate exploring.

2025-03-04

ICLR.cc/2025/Workshop/HAIC (published)

A Guide to Misinformation Detection Data and Evaluation

Camille Thibault

Jacob-Junqi Tian

Gabrielle Peloquin-Skulski

Taylor Lynn Curtis

James Zhou

Florence Laflamme

Luke Yuxiang Guan

Misinformation is a complex societal issue, and mitigating solutions are difficult to create due to data deficiencies. To address this, we h… (see more)ave curated the largest collection of (mis)information datasets in the literature, totaling 75. From these, we evaluated the quality of 36 datasets that consist of statements or claims, as well as the 9 datasets that consist of data in purely paragraph form. We assess these datasets to identify those with solid foundations for empirical work and those with flaws that could result in misleading and non-generalizable results, such as spurious correlations, or examples that are ambiguous or otherwise impossible to assess for veracity. We find the latter issue is particularly severe and affects most datasets in the literature. We further provide state-of-the-art baselines on all these datasets, but show that regardless of label quality, categorical labels may no longer give an accurate evaluation of detection model performance. Finally, we propose and highlight Evaluation Quality Assurance (EQA) as a tool to guide the field toward systemic solutions rather than inadvertently propagating issues in evaluation. Overall, this guide aims to provide a roadmap for higher quality data and better grounded evaluations, ultimately improving research in misinformation detection. All datasets and other artifacts are available at https://misinfo-datasets.complexdatalab.com/.

2024-12-31

ACM SIGKDD Conference on Knowledge Discovery and Data Mining (published)

Online Influence Campaigns: Strategies and Vulnerabilities

Andreea Musulan

Veronica Xia

Ethan Kosak-Hine

Tom Gibbs

Vidya Sujaya

U. Montr'eal

Ivado

M. University

In order to combat the creation and spread of harmful content online, this paper defines and contextualizes the concept of inauthentic, soci… (see more)etal-scale manipulation by malicious actors. We review the literature on societally harmful content and how it proliferates to analyze the manipulation strategies used by such actors and the vulnerabilities they target. We also provide an overview of three case studies of extensive manipulation campaigns to emphasize the severity of the problem. We then address the role that Artificial Intelligence plays in the development and dissemination of harmful content, and how its evolution presents new threats to societal cohesion for countries across the globe. Our survey aims to increase our understanding of not just particular aspects of these threats, but also the strategies underlying their deployment, so we can effectively prepare for the evolving cybersecurity landscape.

2024-12-31

arXiv (preprint)

Open Technical Problems in Open-Weight AI Model Risk Management

Stephen Casper

Kyle O'Brien

Shayne Longpre

Elizabeth Seger

Kevin Klyman

Rishi Bommasani

Aniruddha Nrusimha

Ilia Shumailov

Sören Mindermann

Steven Basart

Frank Rudzicz

Avijit Ghosh

Andrew Strait

Robert Kirk

Dan Hendrycks

Peter Henderson

J. Zico Kolter

Geoffrey Irving

Yarin Gal … (see 2 more)

Yoshua Bengio

Dylan Hadfield-Menell

2024-12-31

SSRN Electronic Journal (accepted)