# MUSER: A MUlti-Step Evidence Retrieval Enhancement Framework for Fake News Detection

arXiv: https://arxiv.org/abs/2306.13450 · HTML: https://mlsanity.com/paper/2306.13450/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jun 2023.

## Built on by (most cited first, 8 of 8)

- [Can LLM-Generated Misinformation Be Detected?](https://mlsanity.com/paper/2309.13788/) (2023)
- [Large Language Models in Argument Mining: A Survey](https://mlsanity.com/paper/2506.16383/) (2025)
- [Web Retrieval Agents for Evidence-Based Misinformation Detection](https://mlsanity.com/paper/2409.00009/) (2024)
- [ESPERANTO: Evaluating Synthesized Phrases to Enhance Robustness in AI Detection for Text Origination](https://mlsanity.com/paper/2409.14285/) (2024)
- [CRAVE: A Conflicting Reasoning Approach for Explainable Claim Verification Using LLMs](https://mlsanity.com/paper/2504.14905/) (2025)
- [LRCTI: A Large Language Model-Based Framework for Multi-Step Evidence Retrieval and Reasoning in Cyber Threat Intelligence Credibility Verification](https://mlsanity.com/paper/2507.11310/) (2025)
- [Verify as You Go: An LLM-Powered Browser Extension for Fake News Detection](https://mlsanity.com/paper/2603.05519/) (2026)
- [A Graph-Enhanced Defense Framework for Explainable Fake News Detection with LLM](https://mlsanity.com/paper/2604.06666/) (2026)

## Abstract (arXiv)

The ease of spreading false information online enables individuals with malicious intent to manipulate public opinion and destabilize social stability. Recently, fake news detection based on evidence retrieval has gained popularity in an effort to identify fake news reliably and reduce its impact. Evidence retrieval-based methods can improve the reliability of fake news detection by computing the textual consistency between the evidence and the claim in the news. In this paper, we propose a framework for fake news detection based on MUlti-Step Evidence Retrieval enhancement (MUSER), which simulates the steps of human beings in the process of reading news, summarizing, consulting materials, and inferring whether the news is true or fake. Our model can explicitly model dependencies among multiple pieces of evidence, and perform multi-step associations for the evidence required for news verification through multi-step retrieval. In addition, our model is able to automatically collect existing evidence through paragraph retrieval and key evidence selection, which can save the tedious process of manual evidence collection. We conducted extensive experiments on real-world datasets in different languages, and the results demonstrate that our proposed model outperforms state-of-the-art baseline methods for detecting fake news by at least 3% in F1-Macro and 4% in F1-Micro. Furthermore, it provides interpretable evidence for end users.