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

arXiv: https://arxiv.org/abs/2609.33441 · HTML: https://mlsanity.com/paper/2609.33441/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 74 references that are in the map.
- First posted on arXiv 27 Sep 2026.

## Builds on (most cited first, 29 of 29)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Leveraging Frequency Analysis for Deep Fake Image Recognition](https://mlsanity.com/paper/2003.08685/) (2020)
- [A Survey on Automated Fact-Checking](https://mlsanity.com/paper/2108.11896/) (2021)
- [Automated Fact-Checking for Assisting Human Fact-Checkers](https://mlsanity.com/paper/2103.07769/) (2021)
- [Visual News: Benchmark and Challenges in News Image Captioning](https://mlsanity.com/paper/2010.03743/) (2020)
- [SNIFFER: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detection](https://mlsanity.com/paper/2403.03170/) (2024)
- [Deepfake Generation and Detection: A Benchmark and Survey](https://mlsanity.com/paper/2403.17881/) (2024)
- [Any-Resolution AI-Generated Image Detection by Spectral Learning](https://mlsanity.com/paper/2411.19417/) (2024)
- [Multimodal Automated Fact-Checking: A Survey](https://mlsanity.com/paper/2305.13507/) (2023)
- [Transform and Tell: Entity-Aware News Image Captioning](https://mlsanity.com/paper/2004.08070/) (2020)
- [AMMeBa: A Large-Scale Survey and Dataset of Media-Based Misinformation In-The-Wild](https://mlsanity.com/paper/2405.11697/) (2024)
- [There is a Time and Place for Reasoning Beyond the Image](https://mlsanity.com/paper/2203.00758/) (2022)
- [MiRAGeNews: Multimodal Realistic AI-Generated News Detection](https://mlsanity.com/paper/2410.09045/) (2024)
- [COVE: COntext and VEracity prediction for out-of-context images](https://mlsanity.com/paper/2502.01194/) (2025)
- [Fact-R1: Towards Explainable Video Misinformation Detection with Deep Reasoning](https://mlsanity.com/paper/2505.16836/) (2025)
- [HEIE: MLLM-Based Hierarchical Explainable AIGC Image Implausibility Evaluator](https://mlsanity.com/paper/2411.17261/) (2024)
- [Similarity over Factuality: Are we making progress on multimodal out-of-context misinformation detection?](https://mlsanity.com/paper/2407.13488/) (2024)
- [M4FC: a Multimodal, Multilingual, Multicultural, Multitask Real-World Fact-Checking Dataset](https://mlsanity.com/paper/2510.23508/) (2025)
- [Characterizing AI-Generated Misinformation on Social Media](https://mlsanity.com/paper/2505.10266/) (2025)
- [DeeCLIP: A Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images](https://mlsanity.com/paper/2504.19876/) (2025)
- [Political Fact-Checking Efforts are Constrained by Deficiencies in Coverage, Speed, and Reach](https://mlsanity.com/paper/2412.13280/) (2024)

## Abstract (arXiv)

Claims paired with AI-generated images are a rapidly growing form of misinformation. Existing automated fact-checking (AFC) methods mainly treat this as a provenance problem, detecting low-level synthesis artifacts to decide whether an image is AI-generated. However, such methods do not verify what human fact-checkers often check: whether an image's content is consistent with the context implied by its accompanying claim. To address this gap, we introduce MIC (Multimodal Inconsistency Checking), an AFC framework that assists human fact-checkers by detecting AI-generated multimodal misinformation and explaining inconsistencies using world knowledge. MIC first uses supervised fine-tuning (SFT) for task adaptation and then applies Group Relative Policy Optimization (GRPO) to directly optimize component-level verifiable rewards for verdict prediction, inconsistency type classification, visual evidence description, and world-knowledge explanation. We further introduce MIC-Bench, a benchmark comprising 8,812 image-claim instances derived from 4,406 claims, where each claim is paired with an authentic image and an AI-generated counterpart that introduces a controlled contextual inconsistency. Compared with SFT alone, GRPO further improves Macro-F1 by 4.67 and 4.11 points in the in-distribution and out-of-distribution settings, respectively, while also improving the semantic similarity of visual evidence descriptions and world-knowledge explanations to reference annotations. Our code and data are available at https://github.com/UKPLab/arxiv2026-mic.