RAGAR, Your Falsehood Radar: RAG-Augmented Reasoning for Political Fact-Checking using Multimodal Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916320276119552 |
|---|---|
| author | Khaliq, M. Abdul Chang, P. Ma, M. Pflugfelder, B. Miletić, F. |
| author_facet | Khaliq, M. Abdul Chang, P. Ma, M. Pflugfelder, B. Miletić, F. |
| contents | The escalating challenge of misinformation, particularly in political discourse, requires advanced fact-checking solutions; this is even clearer in the more complex scenario of multimodal claims. We tackle this issue using a multimodal large language model in conjunction with retrieval-augmented generation (RAG), and introduce two novel reasoning techniques: Chain of RAG (CoRAG) and Tree of RAG (ToRAG). They fact-check multimodal claims by extracting both textual and image content, retrieving external information, and reasoning subsequent questions to be answered based on prior evidence. We achieve a weighted F1-score of 0.85, surpassing a baseline reasoning technique by 0.14 points. Human evaluation confirms that the vast majority of our generated fact-check explanations contain all information from gold standard data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_12065 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RAGAR, Your Falsehood Radar: RAG-Augmented Reasoning for Political Fact-Checking using Multimodal Large Language Models Khaliq, M. Abdul Chang, P. Ma, M. Pflugfelder, B. Miletić, F. Computation and Language Artificial Intelligence Computers and Society Emerging Technologies Multiagent Systems The escalating challenge of misinformation, particularly in political discourse, requires advanced fact-checking solutions; this is even clearer in the more complex scenario of multimodal claims. We tackle this issue using a multimodal large language model in conjunction with retrieval-augmented generation (RAG), and introduce two novel reasoning techniques: Chain of RAG (CoRAG) and Tree of RAG (ToRAG). They fact-check multimodal claims by extracting both textual and image content, retrieving external information, and reasoning subsequent questions to be answered based on prior evidence. We achieve a weighted F1-score of 0.85, surpassing a baseline reasoning technique by 0.14 points. Human evaluation confirms that the vast majority of our generated fact-check explanations contain all information from gold standard data. |
| title | RAGAR, Your Falsehood Radar: RAG-Augmented Reasoning for Political Fact-Checking using Multimodal Large Language Models |
| topic | Computation and Language Artificial Intelligence Computers and Society Emerging Technologies Multiagent Systems |
| url | https://arxiv.org/abs/2404.12065 |