Matches in Nanopublications for { <https://neverblink.eu/ontologies/llm-kg/methods#ReGraM> ?p ?o ?g. }
Showing items 1 to 5 of
5
with 100 items per page.
- ReGraM type Workflow assertion.
- ReGraM label "ReGraM" assertion.
- ReGraM comment "ReGraM is a framework designed to improve the factual accuracy and consistency of Large Language Models (LLMs) in Medical Question Answering. It achieves this by constructing query-aligned subgraphs from a Knowledge Graph (KG) and constraining the LLM's reasoning exclusively within this localized region during the inference phase. This approach directly enhances the LLM's performance on a specific task (QA) by providing structured, relevant external knowledge and guiding its multi-hop reasoning." assertion.
- ReGraM subject KGEnhancedLLMInference assertion.
- ReGraM hasTopCategory KGEnhancedLLM assertion.