mlsanityData to 7 Oct 2026

RAGAR, Your Falsehood Radar: RAG-Augmented Reasoning for Political Fact-Checking using Multimodal Large Language Models

arXiv 2404.12065 ↗First posted 18 Apr 2024cs.CL cs.AI cs.CYcited by 27

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

also in 1 more
Abstract (arXiv)

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.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 8 of its 23 references that are in the map. First posted on arXiv 18 Apr 2024.

Builds on

8 of 23 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Tasks28 Apr

Other references · 7

  1. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  2. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 351
  3. 2023Chain-of-Verification Reduces Hallucination in Large Language Modelscited by 317
  4. 2023FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarioscited by 247
  5. 2023Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Methodcited by 97
  6. 2024JustiLM: Few-shot Justification Generation for Explainable Fact-Checking of Real-world Claimscited by 29
  7. 2024Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Modelscited by 27

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 19; 2026: 6.

27 papers.

Sort:

By area:

  1. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 89
  2. 2025Synthetic Data Generation Using Large Language Models: Advances in Text and Codecited by 61
  3. 2024DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Expertscited by 42
  4. 2025The RAG Paradox: A Black-Box Attack Exploiting Unintentional Vulnerabilities in Retrieval-Augmented Generation Systemscited by 14
  5. 2025Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Modelscited by 13
  6. 2025ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentationcited by 12
  7. 2025RAG Security and Privacy: Formalizing the Threat Model and Attack Surfacecited by 8
  8. 2025The Next Phase of Scientific Fact-Checking: Advanced Evidence Retrieval from Complex Structured Academic Paperscited by 6
  9. 2025XFacta: Contemporary, Real-World Dataset and Evaluation for Multimodal Misinformation Detection with Multimodal LLMscited by 6
  10. 2025Towards Geo-Culturally Grounded LLM Generationscited by 5
  11. 2025T^2Agent A Tool-augmented Multimodal Misinformation Detection Agent with Monte Carlo Tree Searchcited by 4
  12. 2025MAD-Fact: A Multi-Agent Debate Framework for Long-Form Factuality Evaluation in LLMscited by 4
15 more
  1. 2024OrthoDoc: Multimodal Large Language Model for Assisting Diagnosis in Computed Tomographycited by 3
  2. 2025Task-Oriented Automatic Fact-Checking with Frame-Semanticscited by 3
  3. 2025Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioningcited by 2
  4. 2025A Dynamic Knowledge Update-Driven Model with Large Language Models for Fake News Detectioncited by 2
  5. 2025MultiCheck: Strengthening Web Trust with Unified Multimodal Fact Verificationcited by 1
  6. 2025From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Modelscited by 1
  7. 2026Benchmarking Large Language Models for Knowledge Graph Validationcited by 1
  8. 2025Understanding Inequality of LLM Fact-Checking over Geographic Regions with Agent and Retrieval modelscited by 0
  9. 2025Enhancing Critical Thinking with AI: A Tailored Warning System for RAG Modelscited by 0
  10. 2025MERIT: Modular Framework for Multimodal Misinformation Detection with Web-Grounded Reasoningcited by 0
  11. 2026D-SECURE: Dual-Source Evidence Combination for Unified Reasoning in Misinformation Detectioncited by 0
  12. 2026CHAIRO: Contextual Hierarchical Analogical Induction and Reasoning Optimization for LLMscited by 0
  13. 2026CARO: Chain-of-Analogy Reasoning Optimization for Robust Content Moderationcited by 0
  14. 2026PURPOSE: Poisoning Conflict Resolution in RAG via Proxy-Fact-Grounded Updatescited by 0
  15. 2026To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speechcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Large Language Models Require Curated Context for Reliable Political Fact-Checking -- Even with Reasoning and Web Search
  2. 2025Resolving Conflicting Evidence in Automated Fact-Checking: A Study on Retrieval-Augmented LLMs
  3. 2025Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals
  4. 2024Face the Facts! Evaluating RAG-based Pipelines for Professional Fact-Checking
  5. 2024AFaCTA: Assisting the Annotation of Factual Claim Detection with Reliable LLM Annotators
  6. 2025Beyond Retrieval: Improving Evidence Quality for LLM-based Multimodal Fact-Checking
  7. 2025RAMA: Retrieval-Augmented Multi-Agent Framework for Misinformation Detection in Multimodal Fact-Checking
  8. 2025HiFACTMix: A Code-Mixed Benchmark and Graph-Aware Model for EvidenceBased Political Claim Verification in Hinglish