Leveraging long context in retrieval augmented language models for medical question answering

While holding great promise for improving and facilitating healthcare through applications of medical literature summarization, large language models (LLMs) struggle to produce up-to-date responses on evolving topics due to outdated knowledge or hallucination.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…

• AW
  Amazon Web Services
• NI
  National Institutes of Health

  Awards: UL1TR001873, UL1TR002384, R01LM014344
• UN
  U.S. National Library of Medicine

  Awards: UL1TR001873, R01LM014344, R01LM009886, R01LM014573