# Latent Causal Void: Explicit Missing-Context Reconstruction for Misinformation Detection

arXiv: https://arxiv.org/abs/2605.12156 · HTML: https://mlsanity.com/paper/2605.12156/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 33 references that are in the map.
- First posted on arXiv 12 May 2026.

## Builds on (most cited first, 23 of 23)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Fake News Detection on Social Media: A Data Mining Perspective](https://mlsanity.com/paper/1708.01967/) (2017)
- [FKA-Owl: Advancing Multimodal Fake News Detection through Knowledge-Augmented LVLMs](https://mlsanity.com/paper/2403.01988/) (2024)
- [Zoom Out and Observe: News Environment Perception for Fake News Detection](https://mlsanity.com/paper/2203.10885/) (2022)
- [Retrieval Augmented Fact Verification by Synthesizing Contrastive Arguments](https://mlsanity.com/paper/2406.09815/) (2024)
- [The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agents](https://mlsanity.com/paper/2410.19064/) (2024)
- [RAEmoLLM: Retrieval Augmented LLMs for Cross-Domain Misinformation Detection Using In-Context Learning Based on Emotional Information](https://mlsanity.com/paper/2406.11093/) (2024)
- [PCoT: Persuasion-Augmented Chain of Thought for Detecting Fake News and Social Media Disinformation](https://mlsanity.com/paper/2506.06842/) (2025)
- [MSynFD: Multi-hop Syntax aware Fake News Detection](https://mlsanity.com/paper/2402.14834/) (2024)
- [TRUST-VL: An Explainable News Assistant for General Multimodal Misinformation Detection](https://mlsanity.com/paper/2509.04448/) (2025)
- [Harmfully Manipulated Images Matter in Multimodal Misinformation Detection](https://mlsanity.com/paper/2407.19192/) (2024)
- [Evaluating Evidence Attribution in Generated Fact Checking Explanations](https://mlsanity.com/paper/2406.12645/) (2024)
- [A Multi-Agent Framework with Automated Decision Rule Optimization for Cross-Domain Misinformation Detection](https://mlsanity.com/paper/2503.23329/) (2025)
- [Multimodal Fake News Detection: MFND Dataset and Shallow-Deep Multitask Learning](https://mlsanity.com/paper/2505.06796/) (2025)
- [ChronoFact: Timeline-based Temporal Fact Verification](https://mlsanity.com/paper/2410.14964/) (2024)
- [Multimodal Inverse Attention Network with Intrinsic Discriminant Feature Exploitation for Fake News Detection](https://mlsanity.com/paper/2502.01699/) (2025)
- [Attacks by Content: Automated Fact-checking is an AI Security Issue](https://mlsanity.com/paper/2510.11238/) (2025)
- [Robust Misinformation Detection by Visiting Potential Commonsense Conflict](https://mlsanity.com/paper/2504.21604/) (2025)
- [Reasoning About the Unsaid: Misinformation Detection with Omission-Aware Graph Inference](https://mlsanity.com/paper/2512.01728/) (2025)
- [Recon, Answer, Verify: Agents in Search of Truth](https://mlsanity.com/paper/2507.03671/) (2025)
- [Investigating Language and Retrieval Bias in Multilingual Previously Fact-Checked Claim Detection](https://mlsanity.com/paper/2509.25138/) (2025)
- [KG-CRAFT: Knowledge Graph-based Contrastive Reasoning with LLMs for Enhancing Automated Fact-checking](https://mlsanity.com/paper/2601.19447/) (2026)

## Abstract (arXiv)

Automatic misinformation detection performs well when deception is visible in what an article explicitly states. However, some misinformation articles remain locally coherent and only become misleading once compared with contemporaneous reports that supply background facts the article omits. We study this omission-relevant setting and observe that current omission-aware approaches typically either attach retrieved context as auxiliary evidence or infer a categorical omission signal, leaving the specific missing fact implicit. We propose Latent Causal Void (LCV), a retrieval-guided detector that explicitly reconstructs the missing fact for each target sentence and uses it as a textual cross-source relation in graph reasoning. Concretely, LCV retrieves temporally aligned context articles, asks a frozen instruction-tuned large language model to generate a short missing-context description for each sentence--article pair, and feeds the resulting relation text into a heterograph over target sentences and context articles. On the bilingual benchmark of Sheng et al., LCV improves over the strongest omission-aware baseline by 2.56 and 2.84 macro-F1 points on the English and Chinese splits, respectively. The results indicate that modeling the missing cross-source fact itself, rather than only attaching retrieved evidence or predicting an omission signal, is a useful representation for omission-aware misinformation detection.