编辑医疗大型语言模型的事实知识与解释能力
Editing Factual Knowledge and Explanatory Ability of Medical Large Language Models
AI总结：
本文提出MedLaSA策略，通过因果追踪和可扩展适配器精确编辑医疗LLMs的事实知识与解释能力，同时保持无关知识不变。
摘要：
模型编辑旨在精确改变大型语言模型（LLMs）在特定知识方面的行为，同时保持无关知识不变。该方法已被证明在解决LLMs的幻觉和过时信息问题方面有效。然而，尽管在医疗领域解决幻觉是迫切需求，使用模型编辑修改该领域知识的潜力在很大程度上仍未被探索。我们的观察表明，当前方法在处理医疗领域的专业和复杂知识时面临重大挑战。因此，我们提出MedLaSA，一种用于医疗模型编辑的新型分层可扩展适配器策略。MedLaSA结合了添加额外参数和定位后编辑方法的优势。我们利用因果追踪识别不同层神经元间知识的关联，并基于每条知识的关联值生成相应的缩放集。随后，我们将可扩展适配器融入LLMs的密集层。这些适配器根据对应的特定知识被分配缩放值，从而调整适配器的权重和秩。内容越相似，它们之间的缩放越一致。这确保了对语义相同知识的精确编辑，同时避免对无关知识的影响。为评估编辑对LLMs行为的影响，我们提出两项医疗领域的模型编辑研究：(1)编辑医疗专业化的事实知识，(2)编辑复杂知识的解释能力。我们构建了两个新型医疗基准数据集，并引入了一系列具有挑战性和综合性的指标。在医疗LLMs上的大量实验证明了MedLaSA的编辑效率，且不影响无关知识。
英文摘要：
Model editing aims to precisely alter the behaviors of large language models (LLMs) in relation to specific knowledge, while leaving unrelated knowledge intact. This approach has proven effective in addressing issues of hallucination and outdated information in LLMs. However, the potential of using model editing to modify knowledge in the medical field remains largely unexplored, even though resolving hallucination is a pressing need in this area. Our observations indicate that current methods face significant challenges in dealing with specialized and complex knowledge in medical domain. Therefore, we propose MedLaSA, a novel Layer-wise Scalable Adapter strategy for medical model editing. MedLaSA harnesses the strengths of both adding extra parameters and locate-then-edit methods for medical model editing. We utilize causal tracing to identify the association of knowledge in neurons across different layers, and generate a corresponding scale set from the association value for each piece of knowledge. Subsequently, we incorporate scalable adapters into the dense layers of LLMs. These adapters are assigned scaling values based on the corresponding specific knowledge, which allows for the adjustment of the adapter's weight and rank. The more similar the content, the more consistent the scale between them. This ensures precise editing of semantically identical knowledge while avoiding impact on unrelated knowledge. To evaluate the editing impact on the behaviours of LLMs, we propose two model editing studies for medical domain: (1) editing factual knowledge for medical specialization and (2) editing the explanatory ability for complex knowledge. We build two novel medical benchmarking datasets and introduce a series of challenging and comprehensive metrics. Extensive experiments on medical LLMs demonstrate the editing efficiency of MedLaSA, without affecting unrelated knowledge.
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。
