DALK: Dynamic Co-Augmentation of LLMs and KG to answer Alzheimer's Disease Questions with Scientific Literature

TL;DR

DALK introduces a dynamic framework that enhances large language models with a specialized knowledge graph for improved Alzheimer's Disease question answering, demonstrating significant efficacy and providing insights into KG-LLM mutual enhancement.

Contribution

The paper presents a novel dynamic co-augmentation framework that synergistically combines LLMs and knowledge graphs specifically for Alzheimer's Disease research.

Findings

DALK outperforms baseline models on ADQA benchmark

Knowledge graph augmentation improves LLM inference accuracy

Detailed analysis offers insights into KG and LLM mutual enhancement

Abstract

Recent advancements in large language models (LLMs) have achieved promising performances across various applications. Nonetheless, the ongoing challenge of integrating long-tail knowledge continues to impede the seamless adoption of LLMs in specialized domains. In this work, we introduce DALK, a.k.a. Dynamic Co-Augmentation of LLMs and KG, to address this limitation and demonstrate its ability on studying Alzheimer's Disease (AD), a specialized sub-field in biomedicine and a global health priority. With a synergized framework of LLM and KG mutually enhancing each other, we first leverage LLM to construct an evolving AD-specific knowledge graph (KG) sourced from AD-related scientific literature, and then we utilize a coarse-to-fine sampling method with a novel self-aware knowledge retrieval approach to select appropriate knowledge from the KG to augment LLM inference capabilities. The experimental results, conducted on our constructed AD question answering (ADQA) benchmark, underscore the efficacy of DALK. Additionally, we perform a series of detailed analyses that can offer valuable insights and guidelines for the emerging topic of mutually enhancing KG and LLM. We will release the code and data at https://github.com/David-Li0406/DALK.