# Beyond Retrieval: Improving Evidence Quality for LLM-based Multimodal Fact-Checking

arXiv: https://arxiv.org/abs/2505.03135 · HTML: https://mlsanity.com/paper/2505.03135/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 48 references that are in the map.
- First posted on arXiv 6 May 2025.

## Builds on (most cited first, 19 of 19)

- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Fact-Checking Complex Claims with Program-Guided Reasoning](https://mlsanity.com/paper/2305.12744/) (2023)
- [Automated Fact-Checking for Assisting Human Fact-Checkers](https://mlsanity.com/paper/2103.07769/) (2021)
- [Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations](https://mlsanity.com/paper/2411.10414/) (2024)
- [The Fact Extraction and VERification (FEVER) Shared Task](https://mlsanity.com/paper/1811.10971/) (2018)
- [End-to-End Multimodal Fact-Checking and Explanation Generation: A Challenging Dataset and Models](https://mlsanity.com/paper/2205.12487/) (2022)
- [Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method](https://mlsanity.com/paper/2310.00305/) (2023)
- [Explainable Automated Fact-Checking: A Survey](https://mlsanity.com/paper/2011.03870/) (2020)
- [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)
- [Multimodal Automated Fact-Checking: A Survey](https://mlsanity.com/paper/2305.13507/) (2023)
- [DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts](https://mlsanity.com/paper/2412.10510/) (2024)
- [LEMMA: Towards LVLM-Enhanced Multimodal Misinformation Detection with External Knowledge Augmentation](https://mlsanity.com/paper/2402.11943/) (2024)
- [QACHECK: A Demonstration System for Question-Guided Multi-Hop Fact-Checking](https://mlsanity.com/paper/2310.07609/) (2023)
- [News Verifiers Showdown: A Comparative Performance Evaluation of ChatGPT 3.5, ChatGPT 4.0, Bing AI, and Bard in News Fact-Checking](https://mlsanity.com/paper/2306.17176/) (2023)
- [Multi-modal Fake News Detection on Social Media via Multi-grained Information Fusion](https://mlsanity.com/paper/2304.00827/) (2023)
- [Team Triple-Check at Factify 2: Parameter-Efficient Large Foundation Models with Feature Representations for Multi-Modal Fact Verification](https://mlsanity.com/paper/2302.07740/) (2023)

## Built on by (most cited first, 1 of 1)

- [No Hindsight for LLM Fact-Checkers: Measuring Leakage Channels in Misinformation Detection](https://mlsanity.com/paper/2610.04888/) (2026)

## Abstract (arXiv)

The increasing multimodal disinformation, where deceptive claims are reinforced through coordinated text and visual content, poses significant challenges to automated fact-checking. Recent efforts leverage Large Language Models (LLMs) for this task, capitalizing on their strong reasoning and multimodal understanding capabilities. Emerging retrieval-augmented frameworks further equip LLMs with access to open-domain external information, enabling evidence-based verification beyond their internal knowledge. Despite their promising gains, our empirical study reveals notable shortcomings in the external search coverage and evidence quality evaluation. To mitigate those limitations, we propose Aletheia, an end-to-end framework for automated multimodal fact-checking. It introduces a novel evidence retrieval strategy that improves evidence coverage and filters useless information from open-domain sources, enabling the extraction of high-quality evidence for verification. Extensive experiments demonstrate that Aletheia achieves an accuracy of 88.3% on two public multimodal disinformation datasets and 90.2% on newly emerging claims. Compared with existing evidence retrieval strategies, our approach improves verification accuracy by up to 30.8%, highlighting the critical role of evidence quality in LLM-based disinformation verification.