通过RAG和NMISS解决意大利医疗LLM聊天机器人中的幻觉
Addressing Hallucinations with RAG and NMISS in Italian Healthcare LLM Chatbots
AI总结：
本文通过RAG和NMISS方法有效缓解和检测LLM中的幻觉问题，验证了GPT-4和NMISS对提升医疗领域LLM性能的显著效果。
摘要：
我结合检测和缓解技术来解决大型语言模型（LLMs）中的幻觉问题。缓解是在问答检索增强生成（RAG）框架中实现的，而检测则通过引入负缺失信息评分系统（NMISS）来实现，该系统考虑了响应中的上下文相关性。虽然RAG通过将答案基于外部数据来缓解幻觉，但NMISS通过识别传统指标错误地将上下文准确的响应标记为幻觉的情况来细化评估。我使用意大利健康新闻文章作为上下文来评估LLM性能。结果表明，Gemma2和GPT-4优于其他模型，GPT-4生成的答案与参考响应高度一致。中等模型，如Llama2、Llama3和Mistral显著受益于NMISS，突显了它们提供更丰富上下文信息的能力。这种结合方法为LLM中的幻觉减少和更准确的评估提供了新的见解，应用于现实世界的医疗任务和其他领域。
英文摘要：
I combine detection and mitigation techniques to addresses hallucinations in Large Language Models (LLMs). Mitigation is achieved in a question-answering Retrieval-Augmented Generation (RAG) framework while detection is obtained by introducing the Negative Missing Information Scoring System (NMISS), which accounts for contextual relevance in responses. While RAG mitigates hallucinations by grounding answers in external data, NMISS refines the evaluation by identifying cases where traditional metrics incorrectly flag contextually accurate responses as hallucinations. I use Italian health news articles as context to evaluate LLM performance. Results show that Gemma2 and GPT-4 outperform the other models, with GPT-4 producing answers closely aligned with reference responses. Mid-tier models, such as Llama2, Llama3, and Mistral benefit significantly from NMISS, highlighting their ability to provide richer contextual information. This combined approach offers new insights into the reduction and more accurate assessment of hallucinations in LLMs, with applications in real-world healthcare tasks and other domains.
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。
