AsthmaBot：面向哮喘患者支持的多模态、多语言检索增强生成
AsthmaBot: Multi-modal, Multi-Lingual Retrieval Augmented Generation For Asthma Patient Support
AI总结：
针对哮喘患者即时医疗支持需求及大型语言模型易产生幻觉的问题，提出多语言、多模态检索增强生成系统AsthmaBot，整合多数据模态，在常见问题数据集上验证有效并提供在线服务。
摘要：
受环境与生活方式因素影响，全球哮喘发病率不断上升。由于即时医疗服务受限，尤其在发展中国家，亟需自动化支持系统。ChatGPT（Chat Generative Pre-trained Transformer）和Gemini等大型语言模型推动了自然语言处理及问答技术的发展，但易产生事实性错误响应（即幻觉）。整合精选文档的检索增强生成系统可提升大型语言模型性能并降低幻觉发生率。我们提出了AsthmaBot，一个面向哮喘支持的多语言、多模态检索增强生成系统。在哮喘相关常见问题数据集上的评估表明了AsthmaBot的有效性。AsthmaBot附加了交互式直观界面，整合了不同数据模态（文本、图像、视频），使其更易于大众使用。AsthmaBot可通过asthmabot.datanets.org在线访问。
英文摘要：
Asthma rates have risen globally, driven by environmental and lifestyle factors. Access to immediate medical care is limited, particularly in developing countries, necessitating automated support systems. Large Language Models like ChatGPT (Chat Generative Pre-trained Transformer) and Gemini have advanced natural language processing in general and question answering in particular, however, they are prone to producing factually incorrect responses (i.e. hallucinations). Retrieval-augmented generation systems, integrating curated documents, can improve large language models' performance and reduce the incidence of hallucination. We introduce AsthmaBot, a multi-lingual, multi-modal retrieval-augmented generation system for asthma support. Evaluation of an asthma-related frequently asked questions dataset shows AsthmaBot's efficacy. AsthmaBot has an added interactive and intuitive interface that integrates different data modalities (text, images, videos) to make it accessible to the larger public. AsthmaBot is available online via \url{asthmabot.datanets.org}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
