A Browser-based Open Source Assistant for Multimodal Content Verification

Rosanna Milner; Michael Foster; Twin Karmakharm; Olesya Razuvayevskaya; Ian Roberts; Valentin Porcellini; Denis Teyssou; Kalina Bontcheva

cs.CLMar 3, 2026

A Browser-based Open Source Assistant for Multimodal Content Verification

Authors: Rosanna Milner, Michael Foster, Twin Karmakharm, Olesya Razuvayevskaya, Ian Roberts, Valentin Porcellini, Denis Teyssou, Kalina Bontcheva

Organizations: University of Sheffield · AFP Medialab

Abstract

Disinformation and false content produced by generative AI pose a significant challenge for journalists and fact-checkers who must rapidly verify digital media information. While there is an abundance of NLP models for detecting credibility signals such as persuasion techniques, subjectivity, or machine-generated text, such methods often remain inaccessible to non-expert users and are not integrated into their daily workflows as a unified framework. This paper demonstrates the VERIFICATION ASSISTANT, a browser-based tool designed to bridge this gap. The VERIFICATION ASSISTANT, a core component of the widely adopted VERIFICATION PLUGIN (140,000+ users), allows users to submit URLs or media files to a unified interface. It automatically extracts content and routes it to a suite of backend NLP classifiers, delivering actionable credibility signals, estimating AI-generated content, and providing other verification guidance in a clear, easy-to-digest format. This paper showcases the tool architecture, its integration of multiple NLP services, and its real-world application to detecting disinformation.

Figures & tables

Panel of Figure 1 — Figure 1: Requests sent by the assistant when checking a typical webpage.

Figure 2: DBKF text service and Fact Check Semantic Search for simulated data.

Panel of Figure 3 — Figure 3: URL domain analysis results.

Figure 4: Recommended tools for an image.

Panel of Figure 5 — Figure 5: Credibility signals on an AI-generated article.

Figure 6: Named entities extracted from a news article on the war in Ukraine.

Figure 7: Synthesized comments with classifications. Usernames have been blurred to avoid accidental collisions with real (and potentially future) YouTube users.

Figure 8: HTTP response code distribution through 2025.

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Figure 9: Temporal distribution in the number of events (queries) submitted from the Verification Assistant page during 2025.

Automated Fact-Checking

Automated fact-checking detects checkable claims, retrieves evidence, and assesses whether that evidence supports or refutes them.

See all 139 papers

VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation
Sep 28, 2026Hanxun Huang, Yutao Wu, Qizhou Wang +9LLM Evaluation Fake News Detection
The University of Melbourne · Deakin University · Singapore Management University +3
Multi-Agentic System Leveraging Open-Source LLMs to Mitigate Disinformation Threats
Jun 29, 2026Sebastian Kula, Martin TamajkaMulti-Agent LLM Systems Fake News Detection
Kempelen Institute of Intelligent Technologies, Bratislava, Slovakia · West Pomeranian University of Technology in Szczecin, Szczecin, Poland
MIC: Explaining Image-Claim Inconsistencies in AI-Generated Multimodal Misinformation
Sep 27, 2026Ruihong Zeng, Jonathan Tonglet, Preslav Nakov +1Factual Consistency Evaluation Automated Fact-Checking
Mohamed bin Zayed University of Artificial Intelligence, UAE · UKP Lab · Ubiquitous Knowledge Processing Lab (UKP Lab), Department of Computer Science, TU Darmstadt and National Research Center for Applied Cybersecurity ATHENE, Germany +2

Sep 28, 2026J/K move · Enter open · S save

VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation

Hanxun Huang, Yutao Wu, Qizhou Wang, Silvia Montaña-Niño+8

The University of Melbourne · Deakin University · Singapore Management University+3

LLM Evaluation Fake News Detection Automated Fact-Checking

Open paper AskPDF arXiv

Large language models (LLMs) have made misinformation inexpensive to produce but not to verify, creating a growing asymmetry in the information ecosystem. Under tight time, labor, and budget constraints, media organizations, platforms, and fact-checkers rely on screening to prioritize which content to verify. We introduce VEX-Bench, a unified benchmark for evaluating the verification complexity of LLM-generated misinformation, as perceived during screening, across models and generation methods. Verification complexity is assessed along multiple dimensions derived from journalistic and fact-checking practices, capturing checkability, harm potential, source credibility signals, imposter legitimacy, and expected verification effort. We define the VEX score as an integrated measure combining elicitation yield and verification complexity to quantify how generated content consumes limited verification capacity. We construct a benchmark spanning two misinformation categories, 6 high-stakes domains, and 60 real-world topics, and evaluate 7 frontier LLMs and 7 generation methods, yielding 5{,}880 articles. We employ an LLM-as-judge for scalable evaluation and validate it using content-analysis methodology, including ordinal Krippendorff

α

for inter-annotator reliability, complemented by fact-checking agents for verification. Our findings show that no single method dominates all dimensions, underscoring the need for multi-dimensional evaluation. LLMs can generate high-VEX misinformation at 3

\times

to 169

\times

lower cost than agent-based verification. Such content is often prioritized during screening, consuming scarce verification resources and introducing a systematic risk of misallocation in resource-constrained verification systems. The code is publicly available in our GitHub repository.

Abstract

Automated Fact-Checking

Explore similar work

VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation

Multi-Agentic System Leveraging Open-Source LLMs to Mitigate Disinformation Threats

MIC: Explaining Image-Claim Inconsistencies in AI-Generated Multimodal Misinformation