基于幻觉检测的偏好优化用于临床摘要生成
Hallucination Detection-Guided Preference Optimization for Clinical Summarization
AI总结：
提出利用幻觉检测器指导迭代修正的推理时方法及偏好学习微调，显著减少临床摘要中的幻觉。
摘要：
大型语言模型（LLM）在摘要任务上展现出潜力，但常产生幻觉，即无依据或不正确的陈述，限制了其在专业医疗应用中的可靠性。我们引入\itermodelfull（\itermodel），一种推理时方法，利用幻觉检测器指导迭代摘要修正以实现事实更正。在此基础上，我们提出用于偏好学习的\itermodel（\model），将检测器引导的修正轨迹转化为偏好对以进行模型微调。大量实验表明，我们的方法在总结来自\MimicIV的真实临床笔记时，显著减少了Llama和Gemma模型的幻觉。例如，\itermodel在Llama-3.1-8B-Instruct上减少了24%的幻觉，而\model减少了48%。重要的是，根据人类专家和LLM-Jury评估，两种方法都保持了摘要的流畅性、连贯性和相关性。这些结果共同表明，检测信息驱动的修正和偏好学习为提高临床摘要的事实准确性提供了一种自动化解决方案。
英文摘要：
Large language models (LLMs) have shown promise on summarization tasks, but they often produce hallucinations, which are unsupported or incorrect statements that limit their reliability in specialized healthcare applications. We introduce Hallucination Detection Guided Self-Refinement (HDSR), an inference-time method that leverages hallucination detectors to guide iterative summary revisions toward factual corrections. Building on this, we propose HDSR for Preference Learning (HDSR-PL), which converts detector-guided refinement trajectories into preference pairs for model finetuning. Extensive experiments show that our methods substantially reduce hallucinations for Llama and Gemma models in summarizing real-world clinical notes from MIMIC-IV-Note v2.2. For example, HDSR reduces 24% and HDSR-PL reduces 48% hallucinations in Llama-3.1-8B-Instruct. Importantly, both methods preserve summary fluency, coherence, and relevance according to human expert and LLM-Jury evaluations. Together, these results demonstrate that detection-informed refinement and preference learning offer an automated solution for improving factual faithfulness in clinical summarization.
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。
