用检索增强与新评估法减少医疗大模型幻觉
Addressing Hallucinations with RAG and NMISS in Italian Healthcare LLM Chatbots
- 在问答框架中结合外部数据与上下文相关性评分
- GPT-4表现最优，中等模型经优化后显著提升
- 适合医疗等领域需高可信度回答的场景
本文通过检测与缓解相结合的方法，解决大语言模型（LLMs）中的幻觉问题。缓解采用基于检索的生成（RAG）框架，将答案锚定在外部数据上；检测则引入负向缺失信息评分系统（NMISS），考虑回应的上下文相关性。传统指标可能错误地将语义准确的回答判定为幻觉，而NMISS能有效识别此类情况。实验以意大利健康新闻文章为背景，评估模型性能。结果显示，Gemma2和GPT-4优于其他模型，其中GPT-4的答案与参考答案高度一致。中等性能模型如Llama2、Llama3和Mistral在使用NMISS后表现明显改善，表明其具备更强的上下文信息表达能力。该联合方法为降低幻觉并实现更精准评估提供了新思路，适用于医疗等现实任务及其他领域。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。