用RAG提升LLM可靠性：宗教问答中的MufassirQAS
Improving LLM Reliability with RAG in Religious Question-Answering: MufassirQAS
AI总结：
MufassirQAS通过RAG方法提升LLM在宗教问答中的可靠性，提供透明和准确的回应。
摘要：
宗教教义有时复杂难懂，但聊天机器人可以在该领域充当有效的助手。基于大型语言模型（LLM）的聊天机器人，通过自然语言处理（NLP）技术，能够连接相关主题并为复杂问题提供有根据的回答，使其成为宗教教育的宝贵工具。然而，LLM容易产生幻觉，即生成不准确或无关的信息，这些信息可能包含敏感内容，可能具有冒犯性、不适当或争议性。在不无意促进仇恨言论或不尊重某些信仰的情况下处理此类话题仍是一个重大挑战。为了解决这些问题，我们引入了MufassirQAS系统，该系统通过向量数据库驱动的检索增强生成（RAG）方法来提高LLM的准确性和透明度。我们构建了一个包含基本书籍的数据库，其中包含土耳其语翻译和解释的伊斯兰文本。该数据库用于回答宗教问题，同时确保回答可靠且语境相关。我们的系统还展示了相关的数据集部分以及LLM生成的回答，以增强透明度。我们精心设计了系统提示，以防止产生有害、冒犯性或不尊重的输出，确保响应符合道德和尊重的讨论。此外，MufassirQAS还提供补充信息，如来源页面编号和参考文章，以增强可信度。为了评估其有效性，我们测试了MufassirQAS与ChatGPT在敏感问题上的表现，我们的系统在保持准确性和可靠性方面表现出色。未来的工作将专注于提高准确性并完善提示工程技术，以进一步减少偏见并确保更加可靠的响应。
英文摘要：
Religious teachings can sometimes be complex and challenging to grasp, but chatbots can serve as effective assistants in this domain. Large Language Model (LLM) based chatbots, powered by Natural Language Processing (NLP), can connect related topics and provide well-supported responses to intricate questions, making them valuable tools for religious education. However, LLMs are prone to hallucinations as they can generate inaccurate or irrelevant information, and these can include sensitive content that could be offensive, inappropriate, or controversial. Addressing such topics without inadvertently promoting hate speech or disrespecting certain beliefs remains a significant challenge. As a solution to these issues, we introduce MufassirQAS, a system that enhances LLM accuracy and transparency using a vector database-driven Retrieval-Augmented Generation (RAG) approach. We built a dataset comprising fundamental books containing Turkish translations and interpretations of Islamic texts. This database is leveraged to answer religious inquiries while ensuring that responses remain reliable and contextually grounded. Our system also presents the relevant dataset sections alongside the LLM-generated answers, reinforcing transparency. We carefully designed system prompts to prevent harmful, offensive, or disrespectful outputs, ensuring that responses align with ethical and respectful discourse. Moreover, MufassirQAS provides supplementary details, such as source page numbers and referenced articles, to enhance credibility. To evaluate its effectiveness, we tested MufassirQAS against ChatGPT with sensitive questions, and our system demonstrated superior performance in maintaining accuracy and reliability. Future work will focus on improving accuracy and refining prompt engineering techniques to further minimize biases and ensure even more reliable responses.
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。
