@inproceedings{liu-etal-2025-raemollm,
    title = "{RAE}mo{LLM}: Retrieval Augmented {LLM}s for Cross-Domain Misinformation Detection Using In-Context Learning Based on Emotional Information",
    author = "Liu, Zhiwei  and
      Yang, Kailai  and
      Xie, Qianqian  and
      de Kock, Christine  and
      Ananiadou, Sophia  and
      Hovy, Eduard",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.806/",
    pages = "16508--16523",
    ISBN = "979-8-89176-251-0",
    abstract = "Misinformation is prevalent in various fields such as education, politics, health, etc., causing significant harm to society. However, current methods for cross-domain misinformation detection rely on effort- and resource-intensive fine-tuning and complex model structures. With the outstanding performance of LLMs, many studies have employed them for misinformation detection. Unfortunately, they focus on in-domain tasks and do not incorporate significant sentiment and emotion features (which we jointly call \textit{affect}). In this paper, we propose RAEmoLLM, the first retrieval augmented (RAG) LLMs framework to address cross-domain misinformation detection using in-context learning based on affective information. RAEmoLLM includes three modules. (1) In the index construction module, we apply an emotional LLM to obtain affective embeddings from all domains to construct a retrieval database. (2) The retrieval module uses the database to recommend top K examples (text-label pairs) from source domain data for target domain contents. (3) These examples are adopted as few-shot demonstrations for the inference module to process the target domain content. The RAEmoLLM can effectively enhance the general performance of LLMs in cross-domain misinformation detection tasks through affect-based retrieval, without fine-tuning. We evaluate our framework on three misinformation benchmarks. Results show that RAEmoLLM achieves significant improvements compared to the other few-shot methods on three datasets, with the highest increases of 15.64{\%}, 31.18{\%}, and 15.73{\%} respectively. This project is available at https://github.com/lzw108/RAEmoLLM."
}