# Multi-MLLM Knowledge Distillation for Out-of-Context News Detection

arXiv: https://arxiv.org/abs/2505.22517 · HTML: https://mlsanity.com/paper/2505.22517/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge distillation for LLMs, one of 12 directions in Knowledge distillation.
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 28 May 2025.

## Placed in

- Knowledge distillation / [Knowledge distillation for LLMs](https://mlsanity.com/distill/knowledge-distillation-for-llms/)

## Builds on (most cited first, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [Teaching Small Language Models to Reason](https://mlsanity.com/paper/2212.08410/) (2022)
- [Distilling Reasoning Capabilities into Smaller Language Models](https://mlsanity.com/paper/2212.00193/) (2022)
- [Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-Step](https://mlsanity.com/paper/2306.14050/) (2023)
- [Visual News: Benchmark and Challenges in News Image Captioning](https://mlsanity.com/paper/2010.03743/) (2020)
- [NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media](https://mlsanity.com/paper/2104.05893/) (2021)
- [SNIFFER: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detection](https://mlsanity.com/paper/2403.03170/) (2024)
- [Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources](https://mlsanity.com/paper/2112.00061/) (2021)
- [FKA-Owl: Advancing Multimodal Fake News Detection through Knowledge-Augmented LVLMs](https://mlsanity.com/paper/2403.01988/) (2024)
- [Synthetic Misinformers: Generating and Combating Multimodal Misinformation](https://mlsanity.com/paper/2303.01217/) (2023)
- [Support or Refute: Analyzing the Stance of Evidence to Detect Out-of-Context Mis- and Disinformation](https://mlsanity.com/paper/2311.01766/) (2023)
- [Divide-or-Conquer? Which Part Should You Distill Your LLM?](https://mlsanity.com/paper/2402.15000/) (2024)
- [Twitter-COMMs: Detecting Climate, COVID, and Military Multimodal Misinformation](https://mlsanity.com/paper/2112.08594/) (2021)
- [Large Language Models are In-context Teachers for Knowledge Reasoning](https://mlsanity.com/paper/2311.06985/) (2023)
- [Leveraging Chat-Based Large Vision Language Models for Multimodal Out-Of-Context Detection](https://mlsanity.com/paper/2403.08776/) (2024)
- [EXCLAIM: An Explainable Cross-Modal Agentic System for Misinformation Detection with Hierarchical Retrieval](https://mlsanity.com/paper/2504.06269/) (2025)
- [Interpretable Multimodal Out-of-context Detection with Soft Logic Regularization](https://mlsanity.com/paper/2406.04756/) (2024)

## Built on by (most cited first, 2 of 2)

- [Turning Drift into Constraint: Robust Reasoning Alignment in Non-Stationary Multi-Stream Environments](https://mlsanity.com/paper/2510.04142/) (2025)
- [Drive-KD: Multi-Teacher Distillation for VLMs in Autonomous Driving](https://mlsanity.com/paper/2601.21288/) (2026)

## Abstract (arXiv)

Multimodal out-of-context news is a type of misinformation in which the image is used outside of its original context. Many existing works have leveraged multimodal large language models (MLLMs) for detecting out-of-context news. However, observing the limited zero-shot performance of smaller MLLMs, they generally require label-rich fine-tuning and/or expensive API calls to GPT models to improve the performance, which is impractical in low-resource scenarios. In contrast, we aim to improve the performance of small MLLMs in a more label-efficient and cost-effective manner. To this end, we first prompt multiple teacher MLLMs to generate both label predictions and corresponding rationales, which collectively serve as the teachers' knowledge. We then introduce a two-stage knowledge distillation framework to transfer this knowledge to a student MLLM. In Stage 1, we apply LoRA fine-tuning to the student model using all training data. In Stage 2, we further fine-tune the student model using both LoRA fine-tuning and DPO on the data points where teachers' predictions conflict. This two-stage strategy reduces annotation costs and helps the student model uncover subtle patterns in more challenging cases. Experimental results demonstrate that our approach achieves state-of-the-art performance using less than 10% labeled data.