GraphRAG chatbots answer Alzheimer's research questions more comprehensively than plain GPT-4o in LLM-judged comparisons, but reference-level traceability remains unsolved.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Addressing accuracy and hallucination of LLMs in Alzheimer's disease research through knowledge graphs
GraphRAG chatbots answer Alzheimer's research questions more comprehensively than plain GPT-4o in LLM-judged comparisons, but reference-level traceability remains unsolved.