# What's Left Unsaid? Detecting and Correcting Misleading Omissions in Multimodal News Previews

arXiv: https://arxiv.org/abs/2601.05563 · HTML: https://mlsanity.com/paper/2601.05563/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 45 references that are in the map.
- First posted on arXiv 9 Jan 2026.

## Builds on (most cited first, 20 of 20)

- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [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)
- [LEMMA: Towards LVLM-Enhanced Multimodal Misinformation Detection with External Knowledge Augmentation](https://mlsanity.com/paper/2402.11943/) (2024)
- [The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agents](https://mlsanity.com/paper/2410.19064/) (2024)
- [Can LLMs Improve Multimodal Fact-Checking by Asking Relevant Questions?](https://mlsanity.com/paper/2410.04616/) (2024)
- [Beyond the Crowd: LLM-Augmented Community Notes for Governing Health Misinformation](https://mlsanity.com/paper/2510.11423/) (2025)
- [Clickbait Spoiling via Question Answering and Passage Retrieval](https://mlsanity.com/paper/2203.10282/) (2022)
- [Multi-Modal Framing Analysis of News](https://mlsanity.com/paper/2503.20960/) (2025)
- [Truth over Tricks: Measuring and Mitigating Shortcut Learning in Misinformation Detection](https://mlsanity.com/paper/2506.02350/) (2025)
- [Exploring news intent and its application: A theory-driven approach](https://mlsanity.com/paper/2312.16490/) (2023)
- [E2LVLM:Evidence-Enhanced Large Vision-Language Model for Multimodal Out-of-Context Misinformation Detection](https://mlsanity.com/paper/2502.10455/) (2025)
- [The Missing Parts: Augmenting Fact Verification with Half-Truth Detection](https://mlsanity.com/paper/2508.00489/) (2025)
- [Multimodal Clickbait Detection by De-confounding Biases Using Causal Representation Inference](https://mlsanity.com/paper/2410.07673/) (2024)
- [Drifting Away from Truth: GenAI-Driven News Diversity Challenges LVLM-Based Misinformation Detection](https://mlsanity.com/paper/2508.12711/) (2025)
- [Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models](https://mlsanity.com/paper/2505.15489/) (2025)
- [FactGuard: Event-Centric and Commonsense-Guided Fake News Detection](https://mlsanity.com/paper/2511.10281/) (2025)
- [Reasoning About the Unsaid: Misinformation Detection with Omission-Aware Graph Inference](https://mlsanity.com/paper/2512.01728/) (2025)
- [DiFaR: Enhancing Multimodal Misinformation Detection with Diverse, Factual, and Relevant Rationales](https://mlsanity.com/paper/2508.10444/) (2025)

## Built on by (most cited first, 3 of 3)

- [Recursive Self-Evolving Agents via Held-Out Selection](https://mlsanity.com/paper/2606.28374/) (2026)
- [The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation](https://mlsanity.com/paper/2606.03032/) (2026)
- [RCMN: Understanding Misleadingness in Influential Public Discourse](https://mlsanity.com/paper/2608.27358/) (2026)

## Abstract (arXiv)

Even when factually correct, social-media news previews (image-headline pairs) can induce interpretation drift: by selectively omitting crucial context, they lead readers to form judgments that diverge from what the full article supports. This covert harm is subtler than explicit misinformation, yet remains underexplored. To address this gap, we develop a multi-stage pipeline that simulates preview-based and context-based understanding, enabling construction of the MM-Misleading benchmark. Using MM-Misleading, we systematically evaluate open-source LVLMs and uncover pronounced blind spots in omission-based misleadingness detection. We further propose OMGuard, which combines (1) Interpretation-Aware Fine-Tuning for misleadingness detection and (2) Rationale-Guided Misleading Content Correction, where explicit rationales guide headline rewriting to reduce misleading impressions. Experiments show that OMGuard lifts an 8B model's detection accuracy to the level of a 235B LVLM while delivering markedly stronger end-to-end correction. Further analysis shows that misleadingness usually arises from local narrative shifts, such as missing background, instead of global frame changes, and identifies image-driven cases where text-only correction fails, underscoring the need for visual interventions.