用分治策略解决大模型医疗问答中信息丢失问题
A MapReduce Approach to Effectively Utilize Long Context Information in Retrieval Augmented Language Models
- 提出MapReduce式分段处理机制，避免关键信息被淹没
- 在多个医疗QA数据集上提升回答准确率，效果稳定
- 无需修改模型即可增强可靠性，适合医疗场景落地
尽管大语言模型（LLMs）在医疗领域前景广阔，但其在动态话题上常因知识过时或幻觉而产生陈旧回应。检索增强生成（RAG）通过结合搜索引擎与外部知识源，显著提升了响应的准确性与相关性。然而，RAG性能受检索结果中关键信息的排序与密度影响，易出现‘中间信息丢失’问题。本文针对医疗领域提出无需修改模型权重的分治策略BriefContext，有效缓解该问题。实验表明，该方法在多种LLM骨干网络和多个QA数据集上均表现出色，显著提升了RAG流程的鲁棒性与可靠性，有助于提升医疗场景下LLMs的安全性与可信度。
原文摘要 · Abstract (English)
While holding great promise for improving and facilitating healthcare, large language models (LLMs) struggle to produce up-to-date responses on evolving topics due to outdated knowledge or hallucination. Retrieval-augmented generation (RAG) is a pivotal innovation that improves the accuracy and relevance of LLM responses by integrating LLMs with a search engine and external sources of knowledge. However, the quality of RAG responses can be largely impacted by the rank and density of key information in the retrieval results, such as the "lost-in-the-middle" problem. In this work, we aim to improve the robustness and reliability of the RAG workflow in the medical domain. Specifically, we propose a map-reduce strategy, BriefContext, to combat the "lost-in-the-middle" issue without modifying the model weights. We demonstrated the advantage of the workflow with various LLM backbones and on multiple QA datasets. This method promises to improve the safety and reliability of LLMs deployed in healthcare 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。