Explainable multilingual and multimodal fake-news detection: toward robust and trustworthy AI for combating misinformation
Rohini Jadhav, Vishal Meshram, Amol Bhosle, Kailas Patil, Sital Dash, Shrikant Jadhav · 2025
Read Explainable multilingual and multimodal fake-news detection: toward robust and trustworthy AI for combating misinformation by Rohini Jadhav, Vishal Meshram, Amol Bhosle, Kailas Patil, Sital Dash, Shrikant Jadhav (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12727966.txt.
Description
Rohini Jadhav and five co-authors build, in 2025 work, a fake-news spotter that works across tongues and media, and can show its reasons. Most past tools read English text alone and hide their logic. That leaves fact checkers with a score they cannot defend, and leaves other tongues unserved.
The team first built a large data set of news in five tongues, each item paired with a photo. Their model then fuses text, image, and link signals, and explains each call at word, sentence, and media level. It beat two known base models on a fair score, with the biggest gains in low-resource tongues. It held up well against reworded and machine-made fakes. Human judges found most of its reasons sound.
Catalog record
| CREATOR | Rohini Jadhav, Vishal Meshram, Amol Bhosle, Kailas Patil, Sital Dash, Shrikant Jadhav |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 89 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |