Fig. 5: Using biomedical knowledge graphs to defend against misinformation.
From: Medical large language models are vulnerable to data-poisoning attacks
Flowchart of the algorithm steps. First (1), NER is used to extract medical phrases from LLM outputs as biomedical knowledge triplets—origin, relation and target. Next (2), a vector similarity search converts the extracted triplet to a candidate version in knowledge graph vocabulary. Finally (3), candidate triplets are flagged for potential misinformation if they cannot be matched to a connected medical relationship in the knowledge graph.
