Multimodal Climate Disinformation Detection: Integrating Vision-Language Models with External Knowledge Sources
On the map: Multimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Abstract (arXiv)
Climate disinformation has become a major challenge in today digital world, especially with the rise of misleading images and videos shared widely on social media. These false claims are often convincing and difficult to detect, which can delay actions on climate change. While vision-language models (VLMs) have been used to identify visual disinformation, they rely only on the knowledge available at the time of training. This limits their ability to reason about recent events or updates. The main goal of this paper is to overcome that limitation by combining VLMs with external knowledge. By retrieving up-to-date information such as reverse image results, online fact-checks, and trusted expert content, the system can better assess whether an image and its claim are accurate, misleading, false, or unverifiable. This approach improves the model ability to handle real-world climate disinformation and supports efforts to protect public understanding of science in a rapidly changing information landscape.
Key facts. No citing papers in the map yet (data through 13 Oct 2026). Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 9 of its 11 references that are in the map. First posted on arXiv 22 Jan 2026.
Builds on
9 of 11 references.
Closest ancestors · 2
Same direction, newest first
- 2025CMIE: Combining MLLM Insights with External Evidence for Explainable Out-of-Context Misinformation Detection29 May
- 2025Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models21 May
Other references · 7
- 2024LEMMA: Towards LVLM-Enhanced Multimodal Misinformation Detection with External Knowledge Augmentationcited by 28
- 2024GAMED: Knowledge Adaptive Multi-Experts Decoupling for Multimodal Fake News Detectioncited by 11
- 2024Augmented CARDS: A machine learning approach to identifying triggers of climate change misinformation on Twittercited by 4
- 2024Unlearning Climate Misinformation in Large Language Modelscited by 4
- 2025CliME: Evaluating Multimodal Climate Discourse on Social Media and the Climate Alignment Quotient (CAQ)cited by 2
- 2024Promoting Reliable Knowledge about Climate Change: A Systematic Review of Effective Measures to Resist Manipulation on Social Mediacited by 1
- 2025Enhancing LLMs for Governance with Human Oversight: Evaluating and Aligning LLMs on Expert Classification of Climate Misinformation for Detecting False or Misleading Claims about Climate Changecited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025VLDBench Evaluating Multimodal Disinformation with Regulatory Alignment
- 2026From Codebooks to VLMs: Evaluating Automated Visual Discourse Analysis for Climate Change on Social Media
- 2026The Paradigm Shift: A Comprehensive Survey on Large Vision Language Models for Multimodal Fake News Detection
- 2025Effectiveness of Large Multimodal Models in Detecting Disinformation: Experimental Results
- 2025E2LVLM:Evidence-Enhanced Large Vision-Language Model for Multimodal Out-of-Context Misinformation Detection
- 2024Multimodal Misinformation Detection using Large Vision-Language Models
- 2024Multimodal Fact-Checking with Vision Language Models: A Probing Classifier based Solution with Embedding Strategies
- 2026ClimateCheck 2026: Scientific Fact-Checking and Disinformation Narrative Classification of Climate-related Claims