用大模型自动增强数据，让临床文本生成更可控更准确
Towards Conditioning Clinical Text Generation for User Control
- 用大模型模拟医生，自动生成训练数据以提升控制能力
- 在出院记录任务中相对提升9%，数据增强后最高达34%
- 适合关注医疗生成可控性与真实性的研究者与开发者
尽管大型语言模型（LLMs）取得进展，其在临床场景部署仍面临幻觉和事实不一致问题，需人工监督。本文探索利用LLM作为人类代理进行自动化数据集增强，以实现无需增加认知负担的临床医生控制。在BioNLP ACL'24出院记录共享任务中，通过更高效的训练方法取得新基准结果：未使用增强时相对提升9%，使用数据增强后最高达34%。初步人工评估支持该方法在提升相关性、准确性和事实一致性方面的有效性，表明增强临床文本生成的可控性具有广阔前景。
原文摘要 · Abstract (English)
Deploying natural language generation systems in clinical settings remains challenging despite advances in Large Language Models (LLMs), which continue to exhibit hallucinations and factual inconsistencies, necessitating human oversight. This paper explores automated dataset augmentation using LLMs as human proxies to condition LLMs for clinician control without increasing cognitive workload. On the BioNLP ACL'24 Discharge Me! Shared Task, we achieve new state-of-the-art results with simpler methods than prior submissions through more efficient training, yielding a 9\% relative improvement without augmented training and up to 34\% with dataset augmentation. Preliminary human evaluation further supports the effectiveness of our approach, highlighting the potential of augmenting clinical text generation for control to enhance relevance, accuracy, and factual consistency.
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。