---
title: "A Browser-based Open Source Assistant for Multimodal Content"
description: "The authors present the VERIFICATION ASSISTANT, an open-source component of the VERIFICATION PLUGIN Chrome… 16 references."
authors: ["Rosanna Milner", "Michael Foster", "Twin Karmakharm", "Olesya Razuvayevskaya", "Valentin Porcellini", "Denis Teyssou", "Ian Roberts", "Kalina Bontcheva"]
year: 2026
venue: "Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations)"
source: "https://aclanthology.org/2026.eacl-demo.12/"
doi: "10.18653/v1/2026.eacl-demo.12"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/milner-2026-browser-based-open-source-assistant/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/milner-2026-browser-based-open-source-assistant/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/20/) / A Browser-based Open Source Assistant for Multimodal Content Verification

# A Browser-based Open Source Assistant for Multimodal Content Verification

**Authors:** Rosanna Milner, Michael Foster, Twin Karmakharm, Olesya Razuvayevskaya, Valentin Porcellini, Denis Teyssou, Ian Roberts and [Kalina Bontcheva](https://md.research.elamur.ai/free/en/authors/kalina-bontcheva/) · **Year:** 2026 · **Venue:** [Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations)](https://md.research.elamur.ai/free/en/venues/eacl/) ([EACL 2026](https://md.research.elamur.ai/free/en/venues/eacl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.eacl-demo.12/) · [PDF](https://aclanthology.org/2026.eacl-demo.12.pdf) · [DOI 10.18653/v1/2026.eacl-demo.12](https://doi.org/10.18653/v1/2026.eacl-demo.12) · [OpenAlex](https://openalex.org/W7140085197)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Journalists and fact-checkers face a growing amount of disinformation, much of it produced with generative AI. Many NLP models can detect credibility signals, but they usually ship as standalone research models that non-technical users cannot easily run. The authors present the VERIFICATION ASSISTANT, an open-source component of the VERIFICATION PLUGIN Chrome extension. A user submits a URL or uploads an image or video. A Python (Quart) backend then scrapes the text, media and links. The React Redux frontend sends this content in parallel to several microservices, including:
- matching against previously debunked claims (DBKF, Fact Check Semantic Search)
- URL domain credibility checks
- text classifiers, such as topic and persuasion techniques
- named-entity word clouds
- stance classification of YouTube comments
- recommendations for media-forensics tools

The results appear in a single dashboard that gives explanations rather than a bare fake/real verdict. Feedback from fact-checkers shaped the design. A survey of 72 practitioners reported moderate-to-good satisfaction, and usage logs show steady growth during 2025. The work matters because it puts research classifiers directly into everyday verification workflows.

## Key points
- The assistant is part of the VERIFICATION PLUGIN, which has over 140,000 users. The frontend is MIT-licensed on GitHub (AFP-Medialab/verification-plugin) and its interface is available in 10 languages.
- DBKF matching uses the first 100 characters of the text as a title-like query and shows only matches scoring above 40. FCSS compares longer stretches of the text against fact-checking collections.
- For YouTube videos, the top 10 comments and their replies are labelled as support, deny, query or comment.
- At GlobalFact 12, 72 respondents answered a 16-question survey. They rated their frequency of use at 3.75/5 and overall satisfaction at 3.56/5.
- In 2025 the tool received 18,106 requests. Of these, 14.50% returned server errors and 30.82% hit scraper errors. A migration from Webpack to WXT is under way to enable Firefox support.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [University of Sheffield](https://md.research.elamur.ai/free/en/universities/university-of-sheffield/) — University, Sheffield, United Kingdom · 113 works · 21,542 citations

📚 Shelves (7): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,772 works · [🤝 Sociology and Political Science](https://md.research.elamur.ai/free/en/shelves/social-sciences/sociology-and-political-science/) · 577 works

🧭 Topics (1): [🖼️ Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) · 657 works

## Cite

Cite as: Rosanna Milner, Michael Foster, Twin Karmakharm, Olesya Razuvayevskaya, Valentin Porcellini, Denis Teyssou, Ian Roberts and Kalina Bontcheva. 2026. A Browser-based Open Source Assistant for Multimodal Content Verification. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{milner2026browser,
  title = {{A Browser-based Open Source Assistant for Multimodal Content Verification}},
  author = {Rosanna Milner, Michael Foster, Twin Karmakharm, Olesya Razuvayevskaya, Valentin Porcellini, Denis Teyssou, Ian Roberts and Kalina Bontcheva},
  booktitle = {Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations)},
  year = {2026},
  doi = {10.18653/v1/2026.eacl-demo.12},
  url = {https://doi.org/10.18653/v1/2026.eacl-demo.12}
}
```

- [← previous A Binary Problem in Binary QA: Diverse LLMs or Diverse Question Interpretations? That Is the Ensembling Question](https://md.research.elamur.ai/free/en/papers/rosales-2026-binary-problem-binary-qa-diverse/)
- [next → A Cascade Reinforcement Learning Strategy for Efficiently Enhancing the Reasoning Ability of Multimodal Large Language Models](https://md.research.elamur.ai/free/en/papers/wang-2026-cascade-reinforcement-learning/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/20/)

## References

16 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Alberto Barrón-Cedeño, Firoj Alam, Tommaso Caselli, Giovanni Da San Martino, Tamer Elsayed, Andrea Galassi, Fatima Haouari, Federico Ruggeri, Julia Maria Struß, Rabindra Nath Nandi, Gullal S. Cheema, Dilshod Azizov, and Preslav Nakov. 2023. The clef-2023 checkthat! lab: Checkworthiness, subjectivity… [find](https://scholar.google.com/scholar?q=Alberto+Barr%C3%B3n%2DCede%C3%B1o%2C+Firoj+Alam%2C+Tommaso+Caselli%2C+Giovanni+Da+San+Martino%2C+Tamer+Elsayed%2C+Andrea+Galassi%2C+Fatima+Haouari%2C+Federico+Ruggeri%2C+Julia+Maria+Stru%C3%9F%2C+Rabindra+Nath+Nandi%2C+Gullal+S%2E+Cheema%2C+)
2. Giovanni Da San Martino, Shaden Shaar, Yifan Zhang, Seunghak Yu, Alberto Barrón-Cedeño, and Preslav Nakov. 2020. Prta: A system to support the analysis of propaganda techniques in the news. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrati… [find](https://scholar.google.com/scholar?q=Giovanni+Da+San+Martino%2C+Shaden+Shaar%2C+Yifan+Zhang%2C+Seunghak+Yu%2C+Alberto+Barr%C3%B3n%2DCede%C3%B1o%2C+and+Preslav+Nakov%2E+2020%2E+Prta%3A+A+system+to+support+the+analysis+of+propaganda+techniques+in+the+news%2E+In+Proceed)
3. Norbert Fuhr, Anastasia Giachanou, Gregory Grefenstette, Iryna Gurevych, Andreas Hanselowski, Kalervo Jarvelin, Rosie Jones, YiquN Liu, Josiane Mothe, Wolfgang Nejdl, Isabella Peters, and Benno Stein. 2018. An information nutritional label for online documents. SIGIR Forum, 51(3):46–66. [find](https://scholar.google.com/scholar?q=Norbert+Fuhr%2C+Anastasia+Giachanou%2C+Gregory+Grefenstette%2C+Iryna+Gurevych%2C+Andreas+Hanselowski%2C+Kalervo+Jarvelin%2C+Rosie+Jones%2C+YiquN+Liu%2C+Josiane+Mothe%2C+Wolfgang+Nejdl%2C+Isabella+Peters%2C+and+Benno+Stein%2E)
4. Sebastian Gehrmann, Hendrik Strobelt, and Alexander Rush. 2019. [GLTR: Statistical detection and visualization of generated text](https://md.research.elamur.ai/free/en/papers/gehrmann-2019-gltr-statistical-detection-visualization-generated/). In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 111–116, Florence, Italy. Association for Computat…
5. Zhijiang Guo, Michael Sejr Schlichtkrull, and Andreas Vlachos. 2022. [A survey on automated fact-checking](https://md.research.elamur.ai/free/en/papers/guo-2022-survey-automated-fact-checking/). Trans. Assoc. Comput. Linguistics, 10:178–206.
6. Naeemul Hassan, Fatma Arslan, Chengkai Li, and Mark Tremayne. 2017. Toward automated fact-checking: Detecting check-worthy factual claims by claimbuster. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’17, page 1803–1812, New York, NY, USA.… [find](https://scholar.google.com/scholar?q=Naeemul+Hassan%2C+Fatma+Arslan%2C+Chengkai+Li%2C+and+Mark+Tremayne%2E+2017%2E+Toward+automated+fact%2Dchecking%3A+Detecting+check%2Dworthy+factual+claims+by+claimbuster%2E+In+Proceedings+of+the+23rd+ACM+SIGKDD+Internat)
7. Jonas Maab, Eimara Marrese-Taylor, and Sarah Taylor. 2024. Media bias detection across families of language models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 4083–40… [find](https://scholar.google.com/scholar?q=Jonas+Maab%2C+Eimara+Marrese%2DTaylor%2C+and+Sarah+Taylor%2E+2024%2E+Media+bias+detection+across+families+of+language+models%2E+In+Proceedings+of+the+2024+Conference+of+the+North+American+Chapter+of+the+Associati)
8. Dominik Macko, Robert Moro, Adaku Uchendu, Jason Lucas, Michiharu Yamashita, Matúš Pikuliak, Ivan Srba, Thai Le, Dongwon Lee, Jakub Simko, and Maria Bielikova. 2023. MULTITuDE: Large-scale multilingual machine-generated text detection benchmark. In Proceedings of the 2023 Conference on Empirical Met… [find](https://scholar.google.com/scholar?q=Dominik+Macko%2C+Robert+Moro%2C+Adaku+Uchendu%2C+Jason+Lucas%2C+Michiharu+Yamashita%2C+Mat%C3%BA%C5%A1+Pikuliak%2C+Ivan+Srba%2C+Thai+Le%2C+Dongwon+Lee%2C+Jakub+Simko%2C+and+Maria+Bielikova%2E+2023%2E+MULTITuDE%3A+Large%2Dscale+multilingua)
9. Jakub Piskorski, Nicolas Stefanovitch, Giovanni Da San Martino, and Preslav Nakov. 2023. SemEval-2023 task 3: Detecting the category, the framing, and the persuasion techniques in online news in a multilingual setup. In Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2… [find](https://scholar.google.com/scholar?q=Jakub+Piskorski%2C+Nicolas+Stefanovitch%2C+Giovanni+Da+San+Martino%2C+and+Preslav+Nakov%2E+2023%2E+SemEval%2D2023+task+3%3A+Detecting+the+category%2C+the+framing%2C+and+the+persuasion+techniques+in+online+news+in+a+mul)
10. Olesya Razuvayevskaya, Ben Wu, João A. Leite, Freddy Heppell, Ivan Srba, Carolina Scarton, Kalina Bontcheva, and Xingyi Song. 2024. Comparison between parameter-efficient techniques and full fine-tuning: A case study on multilingual news article classification. PLOS ONE, 19(5):e0301738. [find](https://scholar.google.com/scholar?q=Olesya+Razuvayevskaya%2C+Ben+Wu%2C+Jo%C3%A3o+A%2E+Leite%2C+Freddy+Heppell%2C+Ivan+Srba%2C+Carolina+Scarton%2C+Kalina+Bontcheva%2C+and+Xingyi+Song%2E+2024%2E+Comparison+between+parameter%2Defficient+techniques+and+full+fine%2Dtuni)
11. Ipek Baris Schlicht, Lynn Khellaf, and Defne Altiok. 2023. Dwreco at checkthat!-2023: Enhancing subjectivity detection through style-based data sampling. 3497:306–317. [find](https://scholar.google.com/scholar?q=Ipek+Baris+Schlicht%2C+Lynn+Khellaf%2C+and+Defne+Altiok%2E+2023%2E+Dwreco+at+checkthat%21%2D2023%3A+Enhancing+subjectivity+detection+through+style%2Dbased+data+sampling%2E+3497%3A306%E2%80%93317%2E)
12. Karishma Sharma, Feng Qian, He Jiang, Natali Ruchansky, Ming Zhang, and Yan Liu. 2019. Combating fake news: A survey on identification and mitigation techniques. ACM Trans. Intell. Syst. Technol., 10(3). [find](https://scholar.google.com/scholar?q=Karishma+Sharma%2C+Feng+Qian%2C+He+Jiang%2C+Natali+Ruchansky%2C+Ming+Zhang%2C+and+Yan+Liu%2E+2019%2E+Combating+fake+news%3A+A+survey+on+identification+and+mitigation+techniques%2E+ACM+Trans%2E+Intell%2E+Syst%2E+Technol%2E%2C+10%28)
13. Kai Shu, Amy Sliva, Suhang Wang, Jiliang Tang, and Huan Liu. 2017. Fake news detection on social media: A data mining perspective. CoRR, arXiv:1708.01967. — [arXiv:1708.01967](https://arxiv.org/abs/1708.01967) [find](https://scholar.google.com/scholar?q=Kai+Shu%2C+Amy+Sliva%2C+Suhang+Wang%2C+Jiliang+Tang%2C+and+Huan+Liu%2E+2017%2E+Fake+news+detection+on+social+media%3A+A+data+mining+perspective%2E+CoRR%2C+arXiv%3A1708%2E01967%2E+%E2%80%94+%5BarXiv%3A1708%2E01967%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F17)
14. Ivan Srba, Olesya Razuvayevskaya, João A. Leite, Robert Moro, Ipek Baris Schlicht, Sara Tonelli, Francisco Moreno García, Santiago Barrio Lottmann, Denis Teyssou, Valentin Porcellini, Carolina Scarton, Kalina Bontcheva, and Maria Bielikova. 2026. A survey on automatic credibility assessment using te… [find](https://scholar.google.com/scholar?q=Ivan+Srba%2C+Olesya+Razuvayevskaya%2C+Jo%C3%A3o+A%2E+Leite%2C+Robert+Moro%2C+Ipek+Baris+Schlicht%2C+Sara+Tonelli%2C+Francisco+Moreno+Garc%C3%ADa%2C+Santiago+Barrio+Lottmann%2C+Denis+Teyssou%2C+Valentin+Porcellini%2C+Carolina+Scarton)
15. Ben Wu, Olesya Razuvayevskaya, Freddy Heppell, João A. Leite, Carolina Scarton, Kalina Bontcheva, and Xingyi Song. 2023. SheffieldVeraAI at SemEval-2023 task 3: Mono and multilingual approaches for news genre, topic and persuasion technique classification. pages 1995–2008. [find](https://scholar.google.com/scholar?q=Ben+Wu%2C+Olesya+Razuvayevskaya%2C+Freddy+Heppell%2C+Jo%C3%A3o+A%2E+Leite%2C+Carolina+Scarton%2C+Kalina+Bontcheva%2C+and+Xingyi+Song%2E+2023%2E+SheffieldVeraAI+at+SemEval%2D2023+task+3%3A+Mono+and+multilingual+approaches+for+ne)
16. Xinyi Zhou and Reza Zafarani. 2021. A survey of fake news: Fundamental theories, detection methods, and opportunities. ACM Comput. Surv., 53(5):109:1– 109:40. [find](https://scholar.google.com/scholar?q=Xinyi+Zhou+and+Reza+Zafarani%2E+2021%2E+A+survey+of+fake+news%3A+Fundamental+theories%2C+detection+methods%2C+and+opportunities%2E+ACM+Comput%2E+Surv%2E%2C+53%285%29%3A109%3A1%E2%80%93+109%3A40%2E)

*Updated 1 November 2026*