# Customized large language models can outperform Community Notes in correcting misinformation

arXiv: https://arxiv.org/abs/2403.11169 · HTML: https://mlsanity.com/paper/2403.11169/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 63 references that are in the map.
- First posted on arXiv 17 Mar 2024.

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

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation](https://mlsanity.com/paper/2310.03214/) (2023)
- [From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models](https://mlsanity.com/paper/2305.08283/) (2023)
- [Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling](https://mlsanity.com/paper/2104.06967/) (2021)
- [From Show to Tell: A Survey on Deep Learning-based Image Captioning](https://mlsanity.com/paper/2107.06912/) (2021)
- [Factuality Challenges in the Era of Large Language Models](https://mlsanity.com/paper/2310.05189/) (2023)
- [SNIFFER: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detection](https://mlsanity.com/paper/2403.03170/) (2024)
- [Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debate](https://mlsanity.com/paper/2402.07401/) (2024)
- [Reinforcement Learning-based Counter-Misinformation Response Generation: A Case Study of COVID-19 Vaccine Misinformation](https://mlsanity.com/paper/2303.06433/) (2023)
- [JustiLM: Few-shot Justification Generation for Explainable Fact-Checking of Real-world Claims](https://mlsanity.com/paper/2401.08026/) (2024)
- [Fact-checking information from large language models can decrease headline discernment](https://mlsanity.com/paper/2308.10800/) (2023)
- [Birdwatch: Crowd Wisdom and Bridging Algorithms can Inform Understanding and Reduce the Spread of Misinformation](https://mlsanity.com/paper/2210.15723/) (2022)
- [Political Bias and Factualness in News Sharing across more than 100,000 Online Communities](https://mlsanity.com/paper/2102.08537/) (2021)
- [Investigating Differences in Crowdsourced News Credibility Assessment: Raters, Tasks, and Expert Criteria](https://mlsanity.com/paper/2008.09533/) (2020)
- [The effect of source disclosure on evaluation of AI-generated messages: A two-part study](https://mlsanity.com/paper/2311.15544/) (2023)

## Built on by (most cited first, 9 of 9)

- [DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts](https://mlsanity.com/paper/2412.10510/) (2024)
- [Evaluating open-source Large Language Models for automated fact-checking](https://mlsanity.com/paper/2503.05565/) (2025)
- [CMIE: Combining MLLM Insights with External Evidence for Explainable Out-of-Context Misinformation Detection](https://mlsanity.com/paper/2505.23449/) (2025)
- [Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models](https://mlsanity.com/paper/2505.15489/) (2025)
- [Community Moderation and the New Epistemology of Fact Checking on Social Media](https://mlsanity.com/paper/2505.20067/) (2025)
- [Veracity: An Open-Source AI Fact-Checking System](https://mlsanity.com/paper/2506.15794/) (2025)
- [CHASM: Unveiling Covert Advertisements on Chinese Social Media](https://mlsanity.com/paper/2604.20511/) (2026)
- [Using Grok to Avoid Personal Attacks While Correcting Misinformation on X](https://mlsanity.com/paper/2601.04251/) (2026)
- [Unsupervised Anomaly Detection of Information Operations Users via Behavioral and Language Patterns](https://mlsanity.com/paper/2607.05855/) (2026)

## Abstract (arXiv)

Addressing misinformation in real-world settings is challenging: content is often multimodal; factuality judgments are nuanced and context-dependent; new events emerge rapidly across domains; corrections must be timely, trustworthy, and politically impartial; and multidimensional, multistakeholder frameworks remain lacking. Crowdsourced fact-checking systems such as Community Notes have gained broad adoption, but timely, scalable coverage remains difficult. We introduce MUSE, which augments large language models (LLMs) with trust-aware retrieval of up-to-date evidence and task-specific multimodal reasoning. Given a piece of content, MUSE identifies whether and which parts may be false or misleading and provides explanations grounded in credible references. We also develop an evaluation framework that assesses expert-rated response quality---including identification accuracy, explanation factuality, and the relevance and credibility of supporting references---as well as user perceptions. Across social media posts spanning modalities, domains, political leanings, misinformation tactics, and popularity, MUSE consistently produces high-quality responses, including for content not previously fact-checked online, and outperforms even highly rated Community Notes by 29%. It also improves participants' recognition of misinformation by 10%. Our work establishes a general methodological and evaluative framework for timely, scalable, and trustworthy correction of misinformation.